Listings
All listings: OpenRouter
Every listing for the models on page 6 of 26 of OpenRouter, including each model's other versions and routes. Back to OpenRouter
Sold by OpenRouter
117 listings on this page sold by OpenRouter.
Select a score for details.
About these columns
- llminfo IQ
- llminfo IQ (capability index). How llminfo IQ is computed
- Coding IQ
- llminfo Coding IQ (coding capability, its own scale). How Coding IQ is computed
- Value
- Value for money. 50 means as expected for its results. Above 50, cheaper per task. How Value for money works
- Yap
- Tokens used per coding task vs. models with the same results. Includes agents that write code. Chattiness on maths doesn't predict it. How the Yap score works
- Epoch Capabilities Index
- Epoch Capabilities Index benchmark details
| Model | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|
GLM 5V Turbo 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 68 benchmarks. Plenty of data behind it. | 102 ±22Coding IQ 101.9, 95% interval 80–124. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.20cache read $0.24 | $4.00 | 203K | 52.2Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
GLM 5V Turbo Inference by Z.ai🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 68 benchmarks. Plenty of data behind it. | 102 ±22Coding IQ 101.9, 95% interval 80–124. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.20cache read $0.24 | $4.00 | 203K | 52.2Fair value (52.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
MiniMax M3 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.06 | $1.20 | 524K | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.224cache read $0.0448 | $0.88 | 524K | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by Coreweave🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.23cache read $0.05 | $0.96 | 262K | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by DeepInfra🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.224cache read $0.0448 | $0.88 | 524K | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by DeepInfra🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.28cache read $0.056 | $1.10 | 524K | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by DeepInfra🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.224cache read $0.0448 | $0.88 | 524K | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by Featherless AI🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.55cache read $0.06 | $2.20 | 262K | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by Parasail🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.45cache read $0.09 | $1.80 | 1M | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by Parasail🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.06 | $1.20 | 1M | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3 Inference by Venice🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 126.8From 332 benchmarks. Plenty of data behind it. | 107 ±9Coding IQ 107.2, 95% interval 98–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.06 | $1.20 | 524K | 50.9Fair value (50.9). Costs per task about what its benchmark results predict. Plenty of data behind it. | 71 ±8Chatty (71 ±8). Generates more tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 147.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.5 Plus 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 126.8From 53 benchmarks. Plenty of data behind it. | 104 ±7Coding IQ 103.9, 95% interval 97–111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $1.80cache write $0.375 | 1M | 51.4Fair value (51.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 46 ±9Typical (46 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Qwen3.5 Plus Inference by Alibaba Cloud🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 126.8From 53 benchmarks. Plenty of data behind it. | 104 ±7Coding IQ 103.9, 95% interval 97–111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $1.80cache write $0.375 | 984K | 51.4Fair value (51.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 46 ±9Typical (46 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Qwen3.5 122B-A10B 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 126.7From 287 benchmarks. Plenty of data behind it. | 99 ±7Coding IQ 99.3, 95% interval 92–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26 | $2.08 | 262K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Qwen3.5 122B-A10B Inference by Alibaba Cloud🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 126.7From 287 benchmarks. Plenty of data behind it. | 99 ±7Coding IQ 99.3, 95% interval 92–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26 | $2.08 | 258K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Qwen3.5 122B-A10B Inference by Novita AI🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 126.7From 287 benchmarks. Plenty of data behind it. | 99 ±7Coding IQ 99.3, 95% interval 92–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40 | $3.20 | 262K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Qwen3.5 122B-A10B Inference by SiliconFlow🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 126.7From 287 benchmarks. Plenty of data behind it. | 99 ±7Coding IQ 99.3, 95% interval 92–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26 | $2.08 | 262K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Particle 1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | ≈ 126From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.07cache read $0.03 | $0.50 | 1M | —Not enough data yet | —Not measured | —Not measured |
Particle 1 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | ≈ 126From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.00 | $0.00 | 1M | —Not enough data yet | —Not measured | —Not measured |
Particle 1 Inference by Particle AI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | ≈ 126From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.00 | $0.00 | 1M | —Not enough data yet | —Not measured | —Not measured |
Particle 1 Inference by Particle AI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | ≈ 126From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.07cache read $0.03 | $0.50 | 1M | —Not enough data yet | —Not measured | —Not measured |
Particle 1 Inference by Particle AI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | ≈ 126From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.035cache read $0.015 | $0.25 | 1M | —Not enough data yet | —Not measured | —Not measured |
Nemotron 3.5 Super VL 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.15cache read $0.02 | $0.47 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.00 | $0.00 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Baseten🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.20cache read $0.04 | $0.50 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Coreweave🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.15cache read $0.02 | $0.47 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Crusoe🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.10cache read $0.08 | $0.40 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Darkbloom🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.06cache read $0.01 | $0.35 | 262K | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by DeepInfra🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.15cache read $0.02 | $0.50 | 262K | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Ionet🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.09cache read $0.012 | $0.30 | 262K | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Nebius AI Studio🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30cache read $0.06 | $0.90 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by NVIDIA NIM🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.00 | $0.00 | 869K | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by PrimaLabs🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.15cache read $0.02 | $0.50 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Primeintellect🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.15cache read $0.02 | $0.45 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Together AI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.15cache read $0.02 | $0.50 | 262K | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3.5 Super VL Inference by Venice🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.9From 18 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.20cache read $0.04 | $0.50 | 262K | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 54 ±9Typical (54 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | —Not measured |
Step 3.5 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.8From 118 benchmarks. Plenty of data behind it. | 106 ±10Coding IQ 106.2, 95% interval 96–116. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.09cache read $0.02 | $0.30 | —Not published by the provider | 72.1Good value (72.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured |
Ling 3.0 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 52 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.021cache read $0.0042 | $0.063 | 262K | 64.2Good value (64.2). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Ling 3.0 Flash Inference by DeepInfra🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 52 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.06cache read $0.012 | $0.18 | 131K | 64.2Good value (64.2). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Ling 3.0 Flash Inference by Novita AI🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 52 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.021cache read $0.0042 | $0.063 | 262K | 64.2Good value (64.2). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Qwen3.5 27B 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 331 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 100.7, 95% interval 94–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26 | $2.60 | 262K | 42.4Poor value (42.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 56 ±9Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Qwen3.5 27B Inference by Alibaba Cloud🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 331 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 100.7, 95% interval 94–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.195 | $1.56 | 258K | 42.4Poor value (42.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 56 ±9Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Qwen3.5 27B Inference by Chutes🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 331 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 100.7, 95% interval 94–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.20cache read $0.02 | $1.75 | 262K | 42.4Poor value (42.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 56 ±9Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Qwen3.5 27B Inference by DeepInfra🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 331 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 100.7, 95% interval 94–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26 | $2.60 | 262K | 42.4Poor value (42.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 56 ±9Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Qwen3.5 27B Inference by Novita AI🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 331 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 100.7, 95% interval 94–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $2.40 | 262K | 42.4Poor value (42.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 56 ±9Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Qwen3.5 27B Inference by SiliconFlow🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.6From 331 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 100.7, 95% interval 94–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25 | $2.00 | 262K | 42.4Poor value (42.4). Costs more per task than its benchmark results predict. Plenty of data behind it. | 56 ±9Chatty (56 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Solar Mini 4 🇰🇷Maker headquartered in KR, according to the company's own website. The citation is on the model page. | 125.4From 12 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.05cache read $0.005 | $0.20 | 524K | —Not enough data yet | —Not measured | —Not measured |
Solar Mini 4 Inference by Upstage🇰🇷Maker headquartered in KR, according to the company's own website. The citation is on the model page. | 125.4From 12 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.05cache read $0.005 | $0.20 | 524K | —Not enough data yet | —Not measured | —Not measured |
Solar Mini 4 Inference by Upstage🇰🇷Maker headquartered in KR, according to the company's own website. The citation is on the model page. | 125.4From 12 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.05cache read $0.005 | $0.20 | 524K | —Not enough data yet | —Not measured | —Not measured |
Gemini 3.1 Flash Lite 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97 ±10Coding IQ 97.2, 95% interval 88–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25cache read $0.025 | $1.50 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97 ±10Coding IQ 97.2, 95% interval 88–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.125cache read $0.0125 | $0.75 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97 ±10Coding IQ 97.2, 95% interval 88–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25cache read $0.025 | $1.50 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97 ±10Coding IQ 97.2, 95% interval 88–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.125cache read $0.0125 | $0.75 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97 ±10Coding IQ 97.2, 95% interval 88–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.125cache read $0.0125 | $0.75 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97 ±10Coding IQ 97.2, 95% interval 88–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25cache read $0.025 | $1.50 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97 ±10Coding IQ 97.2, 95% interval 88–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.45cache read $0.045 | $2.70 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.1 Flash Lite Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 125.3From 275 benchmarks. Plenty of data behind it. | 97 ±10Coding IQ 97.2, 95% interval 88–107. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.45cache read $0.045 | $2.70 | 1M | 55.5Good value (55.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 145Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Ring 2.6 1T 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 125.3From 14 benchmarks. A fair amount of data behind it. | 102 ±7Coding IQ 102.2, 95% interval 95–109. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.075cache read $0.015 | $0.625 | —Not published by the provider | 51.2Fair value (51.2). Costs per task about what its benchmark results predict. Little data behind it, so treat it as a rough estimate. | 40 ±9Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Gemini Omni 1.1 Flash 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | ≈ 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $1.50 | $9.00 | 131K | —Not enough data yet | —Not measured | —Not measured |
Gemini Omni 1.1 Flash Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | ≈ 125From 8 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $1.50 | $9.00 | 131K | —Not enough data yet | —Not measured | —Not measured |
Grok 4 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 125.2From 296 benchmarks. Plenty of data behind it. | 98 ±13Coding IQ 98.0, 95% interval 85–111. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00 | $15.00 | —Not published by the provider | 32.7Poor value (32.7). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 146.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
125.2From 157 benchmarks. Plenty of data behind it. | 96 ±10Coding IQ 96.3, 95% interval 86–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.20 | $6.00 | —Not published by the provider | 43.3Poor value (43.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 ±9Terse (41 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 142.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
125.2From 157 benchmarks. Plenty of data behind it. | 96 ±10Coding IQ 96.3, 95% interval 86–107. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.78 | $3.90 | —Not published by the provider | 43.3Poor value (43.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 ±9Terse (41 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 142.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V3.2 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.0From 247 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 101.2, 95% interval 94–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26cache read $0.13 | $0.38 | 164K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 Inference by Baidu🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.0From 247 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 101.2, 95% interval 94–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.28cache read $0.028 | $0.42 | 131K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 Inference by DeepInfra🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.0From 247 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 101.2, 95% interval 94–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.26cache read $0.13 | $0.38 | 164K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 Inference by Digitalocean🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.0From 247 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 101.2, 95% interval 94–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.09 | $0.96 | 164K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V3.2 Inference by SiliconFlow🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. Newer version | 125.0From 247 benchmarks. Plenty of data behind it. | 101 ±7Coding IQ 101.2, 95% interval 94–108. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.259cache read $0.14 | $0.80 | 164K | 63.8Good value (63.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | 146.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.0675cache read $0.0375 | $0.225 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Akash🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.07cache read $0.046 | $0.24 | 131K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Cloudflare Workers AI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.05 | $0.30 | 256K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Coreweave🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.10cache read $0.05 | $0.30 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Darkbloom🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.05cache read $0.0125 | $0.19 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by DeepInfra🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.07 | $0.34 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Dekallm🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.06cache read $0.04 | $0.33 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15 | $0.60 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Ionet🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.067cache read $0.039 | $0.29 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Makora🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.09cache read $0.049 | $0.28 | 256K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Nextbit🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.0675cache read $0.0375 | $0.225 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Parasail🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.13cache read $0.05 | $0.40 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Primeintellect🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.082cache read $0.041 | $0.245 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by SiliconFlow🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14cache read $0.05 | $0.40 | 262K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemma 4 26B A4B Inference by Venice🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.9From 216 benchmarks. Plenty of data behind it. | 102 ±8Coding IQ 101.7, 95% interval 94–110. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.13cache read $0.05 | $0.40 | 256K | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. A fair amount of data behind it. | 50 ±9Typical (50 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 141.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
gemini-2.5-flash-preview-09-2025 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 124.7From 26 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30cache read $0.075 | $2.50cache write $0.383 | —Not published by the provider | 63.6Good value (63.6). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured |
GPT-5 mini 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.6From 388 benchmarks. Plenty of data behind it. | 98 ±14Coding IQ 98.3, 95% interval 85–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25cache read $0.025 | $2.00 | 400K | 55.1Good value (55.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 ±9Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 146Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 mini 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.6From 388 benchmarks. Plenty of data behind it. | 98 ±14Coding IQ 98.3, 95% interval 85–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.125cache read $0.0125 | $1.00 | 400K | 55.1Good value (55.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 ±9Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 146Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 mini Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.6From 388 benchmarks. Plenty of data behind it. | 98 ±14Coding IQ 98.3, 95% interval 85–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25cache read $0.03 | $2.00 | 400K | 55.1Good value (55.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 ±9Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 146Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 mini Inference by OpenAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.6From 388 benchmarks. Plenty of data behind it. | 98 ±14Coding IQ 98.3, 95% interval 85–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.25cache read $0.025 | $2.00 | 272K | 55.1Good value (55.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 ±9Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 146Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5 mini Inference by OpenAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.6From 388 benchmarks. Plenty of data behind it. | 98 ±14Coding IQ 98.3, 95% interval 85–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.125cache read $0.0125 | $1.00 | 272K | 55.1Good value (55.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 ±9Terse (40 ±9). Generates fewer tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 146Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Ling 3.0 Flash VL 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | ≈ 125From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.06cache read $0.012 | $0.18 | 131K | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Ling 3.0 Flash VL Inference by DeepInfra🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | ≈ 125From 3 benchmarks. Little data behind it, so treat it as a rough estimate. | —Not enough data yet | $0.06cache read $0.012 | $0.18 | 131K | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
124.4From 11 benchmarks. Plenty of data behind it. | —Not enough data yet | $150.00 | $600.00 | —Not published by the provider | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured | |
Qwen 3 235B A22B Thinking 2507 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.3From 161 benchmarks. Plenty of data behind it. | 100 ±8staleCoding IQ 99.6, 95% interval 91–108. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old. | $0.45cache read $0.10 | $3.50 | 128K | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Qwen 3 235B A22B Thinking 2507 Inference by Venice🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.3From 161 benchmarks. Plenty of data behind it. | 100 ±8staleCoding IQ 99.6, 95% interval 91–108. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. Its newest result is over a year old. | $0.45 | $3.50 | 128K | 40.6Poor value (40.6). Costs more per task than its benchmark results predict. A fair amount of data behind it. | —Not measured | —Not measured |
Grok 4.3 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101 ±8Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.20 | $2.50 | 1M | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Grok 4.3 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101 ±8Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00cache read $0.16 | $2.00 | 1M | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Grok 4.3 Inference by xAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101 ±8Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.20 | $2.50 | 1M | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Grok 4.3 Inference by xAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101 ±8Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00cache read $0.16 | $2.00 | 1M | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Grok 4.3 Inference by xAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101 ±8Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.50cache read $0.40 | $5.00 | 1M | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Grok 4.3 Inference by xAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101 ±8Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.20 | $2.50 | 1M | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Grok 4.3 Inference by xAI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 124.2From 205 benchmarks. Plenty of data behind it. | 101 ±8Coding IQ 101.2, 95% interval 94–109. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.50cache read $0.40 | $5.00 | 1M | 39.3Poor value (39.3). Costs more per task than its benchmark results predict. Plenty of data behind it. | 48 ±9Typical (48 ±9). Generates about as many tokens as models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Nemotron 3 Ultra 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50cache read $0.10 | $2.20 | 262K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | 1M | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by Baseten🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.12 | $2.40 | 203K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by Coreweave🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50cache read $0.10 | $2.15 | 262K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by DeepInfra🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50cache read $0.10 | $2.20 | 262K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by DeepInfra🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.40cache read $0.08 | $1.76 | 262K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by DeepInfra🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.75cache read $0.15 | $3.30 | 262K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by Fireworks AI🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.60cache read $0.12 | $2.40 | 262K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by Kt🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.50cache read $0.10 | $2.20 | 262K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by NVIDIA NIM🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.00 | $0.00 | 1M | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Nemotron 3 Ultra Inference by Venice🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Open weights. The weights are publicly available, according to the provider's model list or a public Hugging Face repo. | 124.1From 172 benchmarks. Plenty of data behind it. | 101 ±12Coding IQ 100.9, 95% interval 89–112. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.625cache read $0.1875 | $3.125 | 256K | 33.1Poor value (33.1). Costs more per task than its benchmark results predict. A fair amount of data behind it. | 53 ±9Typical (53 ±9). Generates about as many tokens as models with similar coding results. Measured with reasoning off. Little data behind it, so treat it as a rough estimate. | 147Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 3.7 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.0From 423 benchmarks. Plenty of data behind it. | 94 ±9Coding IQ 93.6, 95% interval 85–103. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00cache read $0.30 | $15.00cache write $3.75 | —Not published by the provider | 39.2Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 49 ±11Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate. | 141Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 3.7 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 124.0From 423 benchmarks. Plenty of data behind it. | 94 ±9Coding IQ 93.6, 95% interval 85–103. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.00 | $15.00 | —Not published by the provider | 39.2Poor value (39.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 49 ±11Typical (49 ±11). Generates about as many tokens as models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate. | 141Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)