Listings
All listings: Novita AI
Every listing for the models on page 1 of 8 of Novita AI, including each model's other versions and routes. Back to Novita AI
Sold by Novita AI
26 listings on this page sold by Novita AI.
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 |
|---|---|---|---|---|---|---|---|---|
GPT-6.2 Astra 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 17 Nov 2026 | 148.3From 120 benchmarks. Plenty of data behind it. | 142 ±9Coding IQ 141.7, 95% interval 133–150. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $8.00cache read $0.40 | $40.00 | 1.1M | 66.9Good value (66.9). 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 max effort. Little data behind it, so treat it as a rough estimate. | 172.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen4 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | 144.9From 40 benchmarks. Plenty of data behind it. | ≈ 124 ±12Coding IQ 124.3, 95% interval 112–137. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.413cache read $0.071 | $4.24cache write $1.767 | 1M | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured |
GPT-6.2 Sol 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 144.3From 104 benchmarks. Plenty of data behind it. | 139 ±9Coding IQ 139.0, 95% interval 130–148. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.10 | $10.00 | 1.1M | 69.3Good value (69.3). 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 max effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Kimi K3.1 Pro 🇨🇳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. | 142.7From 161 benchmarks. Plenty of data behind it. | 131 ±10Coding IQ 131.3, 95% interval 121–141. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.20 | $10.00cache write $2.00 | 1M | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 51 ±9Typical (51 ±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. | 161.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K3.1 Pro 🇨🇳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. | 142.7From 161 benchmarks. Plenty of data behind it. | 131 ±10Coding IQ 131.3, 95% interval 121–141. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $4.00cache read $0.20 | $20.00cache write $4.00 | 1M | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 51 ±9Typical (51 ±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. | 161.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-6.1 Terra 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 142.5From 130 benchmarks. Plenty of data behind it. | 130 ±13Coding IQ 130.4, 95% interval 118–143. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00cache read $0.05 | $5.00 | 1.1M | 54.7Good value (54.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 52 ±9Typical (52 ±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. | 167.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4.1 Flash 1017 🇨🇳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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127 ±8Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.006 | $1.20 | 1M | 71.4Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Kimi K3 🇨🇳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 | 139.2From 417 benchmarks. Plenty of data behind it. | 124 ±7Coding IQ 123.8, 95% interval 117–131. 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 $3.00 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 158.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Qwen3.8 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117 ±5Coding IQ 117.2, 95% interval 112–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00cache write $2.50 | 1M | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GLM 5.3 🇨🇳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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.26 | $4.40 | 1M | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±10Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
DeepSeek V4.1 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125 ±16Coding IQ 124.7, 95% interval 109–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.006 | $1.20 | 1M | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 ±9Chatty (60 ±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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Hy 4 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.4From 46 benchmarks. Plenty of data behind it. | ≈ 123 ±12Coding IQ 123.4, 95% interval 111–136. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.417cache read $0.021 | $1.2505 | 1M | 56.3Good value (56.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
DeepSeek V4 Pro 0813 🇨🇳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. | 136.8From 147 benchmarks. Plenty of data behind it. | 117 ±7Coding IQ 117.1, 95% interval 110–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.32cache read $0.044 | $3.96 | 1M | 52.5Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±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. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiMo V2.6 Pro 🇨🇳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. | 136.7From 133 benchmarks. Plenty of data behind it. | 123 ±9Coding IQ 123.4, 95% interval 115–132. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.435cache read $0.0036 | $0.87 | 1M | 74.5Good value (74.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±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 |
DeepSeek V4 Flash Vision Exp 🇨🇳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. | 136.6From 32 benchmarks. A fair amount of data behind it. | ≈ 110 ±19Coding IQ 109.6, 95% interval 90–129. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.44cache read $0.028 | $1.32 | 1M | 63.0Good value (63.0). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Hy4 preview 🇨🇳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. | 136.6From 95 benchmarks. Plenty of data behind it. | 118 ±16Coding IQ 118.2, 95% interval 102–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.834cache read $0.042 | $2.501 | 1M | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 ±9Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | —Not measured |
Qwen3.8 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 135.9From 44 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.15cache read $0.016 | $0.47cache write $0.20 | 1M | 65.8Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Ling 3.1 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 | 135.2From 16 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30cache read $0.06 | $0.90 | 1M | 69.6Good value (69.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured |
Qwen3.7 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 134.9From 225 benchmarks. Plenty of data behind it. | 112 ±5Coding IQ 112.2, 95% interval 107–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.25 | $3.75 | 1M | 44.2Poor value (44.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
MiniMax M3.1 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 134.5From 60 benchmarks. Plenty of data behind it. | 119 ±9Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.015 | $0.60 | 1M | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured |
MiMo V2.6 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. | 134.3From 154 benchmarks. Plenty of data behind it. | 116 ±7Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14cache read $0.0028 | $0.28 | 1M | 78.3Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±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 |
133.9From 361 benchmarks. Plenty of data behind it. | 113 ±9Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.26 | $4.40 | 1M | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 ±10Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Ling 3.0 Flash Sante 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 133.8From 6 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.075cache read $0.015 | $0.22 | 262K | —Not enough data yet | —Not measured | —Not measured |
GLM 5.3 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. | 133.6From 266 benchmarks. Plenty of data behind it. | 113 ±8Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.03 | $0.50 | 1M | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 68 ±11Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 153.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Step 5 Preview 🇨🇳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. | 132.7From 119 benchmarks. Plenty of data behind it. | 115 ±7Coding IQ 115.2, 95% interval 108–123. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.00cache read $0.10 | $2.70 | 1M | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured |
Kimi K2.6 🇨🇳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 | 132.6From 305 benchmarks. Plenty of data behind it. | 113 ±7Coding IQ 112.9, 95% interval 106–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.80cache read $0.16 | $3.40 | 262K | 50.4Fair value (50.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 48 ±14Typical (48 ±14). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 151.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Run by Novita AI
60 listings on this page where Novita AI runs the model. Another provider sells these listings.
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 | Provider | llminfo IQ | Coding IQ | Input $/1M | Output $/1M | Max Input Tokens | Value | Yap | Epoch Capabilities Index |
|---|---|---|---|---|---|---|---|---|---|
Qwen4 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | 144.9From 40 benchmarks. Plenty of data behind it. | ≈ 124 ±12Coding IQ 124.3, 95% interval 112–137. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.4837cache read $0.0746 | $4.452 | —Not published by the provider | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured | |
Qwen4 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. NewReleased 11 Nov 2026 | 144.9From 40 benchmarks. Plenty of data behind it. | ≈ 124 ±12Coding IQ 124.3, 95% interval 112–137. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.4837cache read $0.0746 | $4.452 | —Not published by the provider | 61.7Good value (61.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured | |
GPT-6.1 Terra 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 142.5From 130 benchmarks. Plenty of data behind it. | 130 ±13Coding IQ 130.4, 95% interval 118–143. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.05cache read $0.0525 | $5.25 | —Not published by the provider | 54.7Good value (54.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 52 ±9Typical (52 ±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. | 167.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 🇨🇳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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127 ±8Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $1.20 | 1M | 71.4Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 🇨🇳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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127 ±8Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.006 | $1.20 | —Not published by the provider | 71.4Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 🇨🇳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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127 ±8Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.006 | $1.20 | —Not published by the provider | 71.4Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 🇨🇳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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127 ±8Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.1733cache read $0.0035 | $0.693 | —Not published by the provider | 71.4Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 🇨🇳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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127 ±8Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.1733cache read $0.0035 | $0.693 | —Not published by the provider | 71.4Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 1017 🇨🇳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. | 139.7From 97 benchmarks. Plenty of data behind it. | 127 ±8Coding IQ 126.8, 95% interval 119–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.165cache read $0.0033 | $0.66 | 1M | 71.4Good value (71.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 159.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K3 🇨🇳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 | 139.2From 417 benchmarks. Plenty of data behind it. | 124 ±7Coding IQ 123.8, 95% interval 117–131. 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 | $15.00 | —Not published by the provider | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 158.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K3 🇨🇳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 | 139.2From 417 benchmarks. Plenty of data behind it. | 124 ±7Coding IQ 123.8, 95% interval 117–131. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $3.15cache read $0.315 | $15.75 | —Not published by the provider | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±9). Generates about as many tokens as models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 158.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117 ±5Coding IQ 117.2, 95% interval 112–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00 | $6.00 | 1M | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117 ±5Coding IQ 117.2, 95% interval 112–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00 | —Not published by the provider | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117 ±5Coding IQ 117.2, 95% interval 112–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.10cache read $0.2625 | $6.30 | —Not published by the provider | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117 ±5Coding IQ 117.2, 95% interval 112–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.10cache read $0.2625 | $6.30 | —Not published by the provider | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117 ±5Coding IQ 117.2, 95% interval 112–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00 | 1M | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Qwen3.8 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 138.7From 312 benchmarks. Plenty of data behind it. | 117 ±5Coding IQ 117.2, 95% interval 112–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $2.00cache read $0.25 | $6.00 | 1M | 49.2Fair value (49.2). Costs per task about what its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | 157.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 🇨🇳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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40 | $4.40 | 1M | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±10Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 🇨🇳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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.26 | $4.40 | —Not published by the provider | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±10Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 🇨🇳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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.6615cache read $0.1229 | $2.079 | —Not published by the provider | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±10Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 🇨🇳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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.6615cache read $0.1229 | $2.079 | —Not published by the provider | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±10Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 🇨🇳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. | 138.2From 318 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.0, 95% interval 112–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.63cache read $0.117 | $1.98 | 1M | 57.7Good value (57.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±10Chatty (65 ±10). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 157.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125 ±16Coding IQ 124.7, 95% interval 109–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30 | $1.20 | 1M | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 ±9Chatty (60 ±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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125 ±16Coding IQ 124.7, 95% interval 109–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.30cache read $0.006 | $1.20 | —Not published by the provider | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 ±9Chatty (60 ±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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125 ±16Coding IQ 124.7, 95% interval 109–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.1575cache read $0.0032 | $0.63 | —Not published by the provider | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 ±9Chatty (60 ±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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4.1 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.7From 179 benchmarks. Plenty of data behind it. | 125 ±16Coding IQ 124.7, 95% interval 109–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.1575cache read $0.0032 | $0.63 | —Not published by the provider | 68.1Good value (68.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 60 ±9Chatty (60 ±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. | 157Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Hy 4 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 137.4From 46 benchmarks. Plenty of data behind it. | ≈ 123 ±12Coding IQ 123.4, 95% interval 111–136. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.4379cache read $0.0221 | $1.313 | —Not published by the provider | 56.3Good value (56.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 61 ±9Chatty (61 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | —Not measured | |
DeepSeek V4 Pro 0813 🇨🇳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. | 136.8From 147 benchmarks. Plenty of data behind it. | 117 ±7Coding IQ 117.1, 95% interval 110–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.32 | $3.96 | 1M | 52.5Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±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. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Pro 0813 🇨🇳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. | 136.8From 147 benchmarks. Plenty of data behind it. | 117 ±7Coding IQ 117.1, 95% interval 110–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.3167cache read $0.0439 | $3.9501 | —Not published by the provider | 52.5Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±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. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Pro 0813 🇨🇳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. | 136.8From 147 benchmarks. Plenty of data behind it. | 117 ±7Coding IQ 117.1, 95% interval 110–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.3167cache read $0.0439 | $3.9501 | —Not published by the provider | 52.5Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±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. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
DeepSeek V4 Pro 0813 🇨🇳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. | 136.8From 147 benchmarks. Plenty of data behind it. | 117 ±7Coding IQ 117.1, 95% interval 110–124. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.254cache read $0.0418 | $3.762 | 1M | 52.5Fair value (52.5). Costs per task about what its benchmark results predict. Plenty of data behind it. | 58 ±9Chatty (58 ±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. | 156Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
MiMo V2.6 Pro 🇨🇳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. | 136.7From 133 benchmarks. Plenty of data behind it. | 123 ±9Coding IQ 123.4, 95% interval 115–132. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.4568cache read $0.0038 | $0.9135 | —Not published by the provider | 74.5Good value (74.5). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±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 | |
Hy4 preview 🇨🇳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. | 136.6From 95 benchmarks. Plenty of data behind it. | 118 ±16Coding IQ 118.2, 95% interval 102–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.834 | $2.501 | 1M | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 ±9Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | —Not measured | |
Hy4 preview 🇨🇳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. | 136.6From 95 benchmarks. Plenty of data behind it. | 118 ±16Coding IQ 118.2, 95% interval 102–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.834cache read $0.042 | $2.501 | —Not published by the provider | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 ±9Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | —Not measured | |
Hy4 preview 🇨🇳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. | 136.6From 95 benchmarks. Plenty of data behind it. | 118 ±16Coding IQ 118.2, 95% interval 102–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.8757cache read $0.0441 | $2.6261 | —Not published by the provider | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 ±9Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | —Not measured | |
Hy4 preview 🇨🇳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. | 136.6From 95 benchmarks. Plenty of data behind it. | 118 ±16Coding IQ 118.2, 95% interval 102–135. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.834cache read $0.042 | $2.501 | 1M | 56.4Good value (56.4). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 57 ±9Chatty (57 ±9). Generates more tokens than models with similar coding results. Measured at max effort. Little data behind it, so treat it as a rough estimate. | —Not measured | |
Qwen3.8 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 135.9From 44 benchmarks. Plenty of data behind it. | —Not enough data yet | $0.15cache read $0.016 | $0.47 | —Not published by the provider | 65.8Good value (65.8). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured | |
Ling 3.1 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 | 135.2From 16 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30 | $0.90 | 1M | 69.6Good value (69.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured | |
Ling 3.1 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 | 135.2From 16 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.30cache read $0.06 | $0.90 | —Not published by the provider | 69.6Good value (69.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured | |
Ling 3.1 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 | 135.2From 16 benchmarks. A fair amount of data behind it. | —Not enough data yet | $0.06cache read $0.012 | $0.18 | 1M | 69.6Good value (69.6). Cheaper per task than its benchmark results predict. Little data behind it, so treat it as a rough estimate. | —Not measured | —Not measured | |
Qwen3.7 Max 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. Newer version | 134.9From 225 benchmarks. Plenty of data behind it. | 112 ±5Coding IQ 112.2, 95% interval 107–117. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.25cache read $0.25 | $3.75 | —Not published by the provider | 44.2Poor value (44.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 55 ±9Typical (55 ±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. | 154.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
MiniMax M3.1 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 134.5From 60 benchmarks. Plenty of data behind it. | 119 ±9Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.015 | $0.60 | —Not published by the provider | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured | |
MiniMax M3.1 Flash 🇨🇳Maker headquartered in CN, according to the company's own website. The citation is on the model page. | 134.5From 60 benchmarks. Plenty of data behind it. | 119 ±9Coding IQ 118.7, 95% interval 109–128. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.1575cache read $0.0158 | $0.63 | —Not published by the provider | 60.2Good value (60.2). Cheaper per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured | |
MiMo V2.6 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. | 134.3From 154 benchmarks. Plenty of data behind it. | 116 ±7Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.14 | $0.28 | 1M | 78.3Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±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 | |
MiMo V2.6 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. | 134.3From 154 benchmarks. Plenty of data behind it. | 116 ±7Coding IQ 115.7, 95% interval 109–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.147cache read $0.0029 | $0.294 | —Not published by the provider | 78.3Good value (78.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 62 ±9Chatty (62 ±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 | |
133.9From 361 benchmarks. Plenty of data behind it. | 113 ±9Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40 | $4.40 | 1M | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 ±10Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
133.9From 361 benchmarks. Plenty of data behind it. | 113 ±9Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.40cache read $0.26 | $4.40 | —Not published by the provider | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 ±10Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
133.9From 361 benchmarks. Plenty of data behind it. | 113 ±9Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.47cache read $0.273 | $4.62 | —Not published by the provider | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 ±10Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
133.9From 361 benchmarks. Plenty of data behind it. | 113 ±9Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.47cache read $0.273 | $4.62 | —Not published by the provider | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 ±10Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
133.9From 361 benchmarks. Plenty of data behind it. | 113 ±9Coding IQ 113.3, 95% interval 105–122. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.77cache read $0.143 | $2.42 | 1M | 45.9Poor value (45.9). Costs more per task than its benchmark results predict. Plenty of data behind it. | 58 ±10Chatty (58 ±10). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate. | 153.1Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | ||
GLM 5.3 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. | 133.6From 266 benchmarks. Plenty of data behind it. | 113 ±8Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15 | $0.50 | 1M | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 68 ±11Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 153.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 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. | 133.6From 266 benchmarks. Plenty of data behind it. | 113 ±8Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.15cache read $0.03 | $0.50 | —Not published by the provider | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 68 ±11Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 153.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 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. | 133.6From 266 benchmarks. Plenty of data behind it. | 113 ±8Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.0882cache read $0.0176 | $0.294 | —Not published by the provider | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 68 ±11Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 153.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
GLM 5.3 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. | 133.6From 266 benchmarks. Plenty of data behind it. | 113 ±8Coding IQ 112.8, 95% interval 105–120. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.084cache read $0.0168 | $0.28 | 1M | 65.3Good value (65.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 68 ±11Chatty (68 ±11). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 153.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Step 5 Preview 🇨🇳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. | 132.7From 119 benchmarks. Plenty of data behind it. | 115 ±7Coding IQ 115.2, 95% interval 108–123. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $1.05cache read $0.105 | $2.835 | —Not published by the provider | 43.2Poor value (43.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | —Not measured | —Not measured | |
Kimi K2.6 🇨🇳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 | 132.6From 305 benchmarks. Plenty of data behind it. | 113 ±7Coding IQ 112.9, 95% interval 106–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.80 | $3.40 | 262K | 50.4Fair value (50.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 48 ±14Typical (48 ±14). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 151.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K2.6 🇨🇳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 | 132.6From 305 benchmarks. Plenty of data behind it. | 113 ±7Coding IQ 112.9, 95% interval 106–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.80cache read $0.16 | $3.40 | —Not published by the provider | 50.4Fair value (50.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 48 ±14Typical (48 ±14). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 151.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K2.6 🇨🇳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 | 132.6From 305 benchmarks. Plenty of data behind it. | 113 ±7Coding IQ 112.9, 95% interval 106–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.84cache read $0.168 | $3.57 | —Not published by the provider | 50.4Fair value (50.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 48 ±14Typical (48 ±14). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 151.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K2.6 🇨🇳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 | 132.6From 305 benchmarks. Plenty of data behind it. | 113 ±7Coding IQ 112.9, 95% interval 106–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.84cache read $0.168 | $3.57 | —Not published by the provider | 50.4Fair value (50.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 48 ±14Typical (48 ±14). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 151.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API | |
Kimi K2.6 🇨🇳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 | 132.6From 305 benchmarks. Plenty of data behind it. | 113 ±7Coding IQ 112.9, 95% interval 106–119. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | $0.80cache read $0.16 | $3.40 | 262K | 50.4Fair value (50.4). Costs per task about what its benchmark results predict. Plenty of data behind it. | 48 ±14Typical (48 ±14). Generates about as many tokens as models with similar coding results. Measured at default effort. A fair amount of data behind it. | 151.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)