Listings
All listings: Cortecs AI
Every listing for the models on page 1 of 5 of Cortecs AI, including each model's other versions and routes. Back to Cortecs AI
Sold by Cortecs AI
80 listings on this page sold by Cortecs 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 |
|---|---|---|---|---|---|---|---|---|
Gemini 4 Neon 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 18 Nov 2026 | 150.3From 88 benchmarks. Plenty of data behind it. | ≈ 126 ±31Coding IQ 126.2, 95% interval 95–157. 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. | €3.063cache read €0.153≈ $3.3613 USD (sorted by USD value) | €15.315≈ $16.8065 USD (sorted by USD value) | 1M | 49.5Fair value (49.5). Costs per task about what its benchmark results predict. A fair amount of data behind it. | 60 ±9Chatty (60 ±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 |
Gemini 4 Neon Inference by Google Priority🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 18 Nov 2026 | 150.3From 88 benchmarks. Plenty of data behind it. | ≈ 126 ±31Coding IQ 126.2, 95% interval 95–157. 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. | — | — | 1M | 49.5Fair value (49.5). Costs per task about what its benchmark results predict. A fair amount of data behind it. | 60 ±9Chatty (60 ±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 |
Gemini 4 Neon Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 18 Nov 2026 | 150.3From 88 benchmarks. Plenty of data behind it. | ≈ 126 ±31Coding IQ 126.2, 95% interval 95–157. 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. | — | — | 1M | 49.5Fair value (49.5). Costs per task about what its benchmark results predict. A fair amount of data behind it. | 60 ±9Chatty (60 ±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 |
Gemini 4 Carbon 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 10 Nov 2026 | 149.4From 127 benchmarks. Plenty of data behind it. | 144 ±11Coding IQ 143.6, 95% interval 133–155. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €2.001cache read €0.10≈ $2.1959 USD (sorted by USD value) | €10.005≈ $10.9794 USD (sorted by USD value) | 1M | 72.1Good value (72.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 53 ±9Typical (53 ±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. | 169.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 4 Carbon Inference by Google Priority🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 10 Nov 2026 | 149.4From 127 benchmarks. Plenty of data behind it. | 144 ±11Coding IQ 143.6, 95% interval 133–155. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 72.1Good value (72.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 53 ±9Typical (53 ±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. | 169.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 4 Carbon Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 10 Nov 2026 | 149.4From 127 benchmarks. Plenty of data behind it. | 144 ±11Coding IQ 143.6, 95% interval 133–155. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 72.1Good value (72.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 53 ±9Typical (53 ±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. | 169.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
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. | €8.909cache read €0.446≈ $9.7766 USD (sorted by USD value) | €44.544cache write €11.136≈ $48.882 USD (sorted by USD value) | 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 |
GPT-6.2 Astra Inference by Microsoft Azure🇺🇸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. | — | — | 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 |
GPT-6 Astra 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 147.2From 338 benchmarks. Plenty of data behind it. | 139 ±6Coding IQ 138.9, 95% interval 133–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €11.138cache read €1.114≈ $12.2227 USD (sorted by USD value) | €55.692cache write €13.923≈ $61.1156 USD (sorted by USD value) | 1.1M | 62.1Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 37 ±8Terse (37 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 169.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-6 Astra Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 147.2From 338 benchmarks. Plenty of data behind it. | 139 ±6Coding IQ 138.9, 95% interval 133–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1.1M | 62.1Good value (62.1). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 37 ±8Terse (37 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 169.2Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 5.5 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 146.6From 329 benchmarks. Plenty of data behind it. | 147 ±5Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €4.083cache read €0.204≈ $4.4806 USD (sorted by USD value) | €20.416cache write €5.104≈ $22.4042 USD (sorted by USD value) | 1M | 66.8Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±12Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 168.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 5.5 Inference by Amazon Web Services🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 146.6From 329 benchmarks. Plenty of data behind it. | 147 ±5Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 66.8Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±12Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 168.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 5.5 Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 146.6From 329 benchmarks. Plenty of data behind it. | 147 ±5Coding IQ 147.1, 95% interval 142–152. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 66.8Good value (66.8). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 65 ±12Chatty (65 ±12). Generates more tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 168.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 4 Hydrogen 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 12 Nov 2026 | 146.6From 107 benchmarks. Plenty of data behind it. | 126 ±11Coding IQ 125.7, 95% interval 115–137. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €1.515cache read €0.076≈ $1.6625 USD (sorted by USD value) | €7.574≈ $8.3116 USD (sorted by USD value) | 1M | 65.1Good value (65.1). 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 default effort. Little data behind it, so treat it as a rough estimate. | 166.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 4 Hydrogen Inference by Google Priority🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 12 Nov 2026 | 146.6From 107 benchmarks. Plenty of data behind it. | 126 ±11Coding IQ 125.7, 95% interval 115–137. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 65.1Good value (65.1). 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 default effort. Little data behind it, so treat it as a rough estimate. | 166.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 4 Hydrogen Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. NewReleased 12 Nov 2026 | 146.6From 107 benchmarks. Plenty of data behind it. | 126 ±11Coding IQ 125.7, 95% interval 115–137. A fair amount of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 65.1Good value (65.1). 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 default effort. Little data behind it, so treat it as a rough estimate. | 166.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-6.1 Sol 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 145.6From 239 benchmarks. Plenty of data behind it. | 135 ±16Coding IQ 135.0, 95% interval 119–151. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €2.228cache read €0.111≈ $2.445 USD (sorted by USD value) | €11.138cache write €2.785≈ $12.2227 USD (sorted by USD value) | 1.1M | 68.3Good value (68.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 51 ±11Typical (51 ±11). 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. | 168.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-6.1 Sol Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 145.6From 239 benchmarks. Plenty of data behind it. | 135 ±16Coding IQ 135.0, 95% interval 119–151. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1.1M | 68.3Good value (68.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 51 ±11Typical (51 ±11). 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. | 168.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 4 Argon 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 145.4From 217 benchmarks. Plenty of data behind it. | 139 ±9Coding IQ 139.0, 95% interval 130–148. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €2.02cache read €0.101≈ $2.2167 USD (sorted by USD value) | €10.098≈ $11.0814 USD (sorted by USD value) | 1M | 66.0Good value (66.0). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 66 ±9Chatty (66 ±9). Generates more tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate. | 166.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 4 Argon Inference by Google Priority🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 145.4From 217 benchmarks. Plenty of data behind it. | 139 ±9Coding IQ 139.0, 95% interval 130–148. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 66.0Good value (66.0). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 66 ±9Chatty (66 ±9). Generates more tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate. | 166.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 4 Argon Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 145.4From 217 benchmarks. Plenty of data behind it. | 139 ±9Coding IQ 139.0, 95% interval 130–148. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 66.0Good value (66.0). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 66 ±9Chatty (66 ±9). Generates more tokens than models with similar coding results. Measured at high effort. Little data behind it, so treat it as a rough estimate. | 166.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
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. | €2.228cache read €0.111≈ $2.445 USD (sorted by USD value) | €11.138cache write €2.785≈ $12.2227 USD (sorted by USD value) | 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 |
GPT-6.2 Sol Inference by Microsoft Azure🇺🇸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. | — | — | 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 |
Claude Opus 5 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 143.9From 389 benchmarks. Plenty of data behind it. | 134 ±6Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €5.105cache read €0.511≈ $5.6022 USD (sorted by USD value) | €25.526cache write €6.381≈ $28.0119 USD (sorted by USD value) | 1M | 64.6Good value (64.6). 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. A fair amount of data behind it. | 164.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 5 Inference by Amazon Web Services🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 143.9From 389 benchmarks. Plenty of data behind it. | 134 ±6Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 64.6Good value (64.6). 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. A fair amount of data behind it. | 164.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 5 Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 143.9From 389 benchmarks. Plenty of data behind it. | 134 ±6Coding IQ 133.8, 95% interval 128–140. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 64.6Good value (64.6). 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. A fair amount of data behind it. | 164.7Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 5.5 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 143.9From 270 benchmarks. Plenty of data behind it. | 140 ±5Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €2.042cache read €0.102≈ $2.2409 USD (sorted by USD value) | €10.208cache write €2.551≈ $11.2021 USD (sorted by USD value) | 1M | 66.7Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 38 ±9Terse (38 ±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. | 166.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 5.5 Inference by Amazon Web Services🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 143.9From 270 benchmarks. Plenty of data behind it. | 140 ±5Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 66.7Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 38 ±9Terse (38 ±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. | 166.6Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Sonnet 5.5 Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 143.9From 270 benchmarks. Plenty of data behind it. | 140 ±5Coding IQ 140.0, 95% interval 135–145. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 66.7Good value (66.7). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 38 ±9Terse (38 ±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. | 166.6Epoch 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. | €1.833cache read €0.183≈ $2.0115 USD (sorted by USD value) | €9.164≈ $10.0564 USD (sorted by USD value) | 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 Inference by Arkane🇨🇳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. | — | — | 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 Inference by Berget 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. | 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. | — | — | 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 Inference by Tensorix🇨🇳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. | — | — | 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. | €1.114cache read €0.056≈ $1.2225 USD (sorted by USD value) | €5.569cache write €1.392≈ $6.1113 USD (sorted by USD value) | 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 |
GPT-6.1 Terra Inference by Microsoft Azure🇺🇸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. | — | — | 1.1M | 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 |
GPT-6 Sol 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 142.5From 210 benchmarks. Plenty of data behind it. | 130 ±7Coding IQ 129.5, 95% interval 123–136. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €2.228cache read €0.223≈ $2.445 USD (sorted by USD value) | €11.138cache write €2.785≈ $12.2227 USD (sorted by USD value) | 1.1M | 63.4Good value (63.4). 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. | 163.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-6 Sol Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 142.5From 210 benchmarks. Plenty of data behind it. | 130 ±7Coding IQ 129.5, 95% interval 123–136. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1.1M | 63.4Good value (63.4). 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. | 163.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.6 Sol 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 141.6From 504 benchmarks. Plenty of data behind it. | 125 ±5Coding IQ 125.1, 95% interval 120–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €4.083cache read €0.408≈ $4.4806 USD (sorted by USD value) | €20.416cache write €5.105≈ $22.4042 USD (sorted by USD value) | 1.1M | 59.9Good value (59.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 41 ±8Terse (41 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 163Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
GPT-5.6 Sol Inference by Microsoft Azure🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 141.6From 504 benchmarks. Plenty of data behind it. | 125 ±5Coding IQ 125.1, 95% interval 120–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1.1M | 59.9Good value (59.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 41 ±8Terse (41 ±8). Generates fewer tokens than models with similar coding results. Measured at max effort. A fair amount of data behind it. | 163Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.8 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 139.7From 478 benchmarks. Plenty of data behind it. | 121 ±4Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €5.105cache read €0.511≈ $5.6022 USD (sorted by USD value) | €25.526cache write €6.381≈ $28.0119 USD (sorted by USD value) | 1M | 52.9Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 ±10Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 159.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.8 Inference by Amazon Web Services🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 139.7From 478 benchmarks. Plenty of data behind it. | 121 ±4Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 52.9Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 ±10Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 159.9Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.8 Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 139.7From 478 benchmarks. Plenty of data behind it. | 121 ±4Coding IQ 120.8, 95% interval 116–125. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 52.9Good value (52.9). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 40 ±10Terse (40 ±10). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 159.9Epoch 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. | €0.092cache read €0.005≈ $0.101 USD (sorted by USD value) | €0.55≈ $0.6036 USD (sorted by USD value) | 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 Inference by Aki🇨🇳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. | — | — | 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 Inference by Arkane🇨🇳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. | — | — | 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 Inference by Entrim🇨🇳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. | — | — | 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 Inference by Inceptron🇨🇳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. | — | — | 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 Inference by OVHcloud🇨🇳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. | — | — | 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 Inference by Scaleway🇨🇳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. | — | — | 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 Inference by Sference🇨🇳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. | — | — | 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 Inference by Tensorix🇨🇳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. | — | — | 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 |
Gemini 3.8 Flash 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 139.6From 325 benchmarks. Plenty of data behind it. | 121 ±8Coding IQ 121.0, 95% interval 113–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €0.741cache read €0.074≈ $0.8132 USD (sorted by USD value) | €3.703≈ $4.0636 USD (sorted by USD value) | 1M | 55.0Good value (55.0). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 64 ±10Chatty (64 ±10). Generates more tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it. | 158.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.8 Flash Inference by Google Priority🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 139.6From 325 benchmarks. Plenty of data behind it. | 121 ±8Coding IQ 121.0, 95% interval 113–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 55.0Good value (55.0). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 64 ±10Chatty (64 ±10). Generates more tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it. | 158.8Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.8 Flash Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. | 139.6From 325 benchmarks. Plenty of data behind it. | 121 ±8Coding IQ 121.0, 95% interval 113–129. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 55.0Good value (55.0). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 64 ±10Chatty (64 ±10). Generates more tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it. | 158.8Epoch 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. | €2.693≈ $2.9553 USD (sorted by USD value) | €13.464≈ $14.7752 USD (sorted by USD value) | 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 |
Kimi K3 Inference by Arkane🇨🇳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. | — | — | 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 |
Kimi K3 Inference by Nebius AI Studio🇨🇳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. | — | — | 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 |
Gemini 3.7 Flash 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 138.8From 267 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.3, 95% interval 113–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €0.673cache read €0.067≈ $0.7385 USD (sorted by USD value) | €3.366≈ $3.6938 USD (sorted by USD value) | 1M | 60.3Good value (60.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 59 ±12Chatty (59 ±12). Generates more tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it. | 158.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.7 Flash Inference by Google Priority🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 138.8From 267 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.3, 95% interval 113–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 60.3Good value (60.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 59 ±12Chatty (59 ±12). Generates more tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it. | 158.4Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Gemini 3.7 Flash Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 138.8From 267 benchmarks. Plenty of data behind it. | 121 ±9Coding IQ 121.3, 95% interval 113–130. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 60.3Good value (60.3). Cheaper per task than its benchmark results predict. Plenty of data behind it. | 59 ±12Chatty (59 ±12). Generates more tokens than models with similar coding results. Measured at high effort. A fair amount of data behind it. | 158.4Epoch 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. | €2.244cache read €0.561≈ $2.4625 USD (sorted by USD value) | €5.386≈ $5.9105 USD (sorted by USD value) | 262K | 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 Inference by Tensorix🇨🇳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. | — | — | 262K | 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 |
Claude Opus 4.7 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 138.2From 354 benchmarks. Plenty of data behind it. | 118 ±15Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €5.105cache read €0.511≈ $5.6022 USD (sorted by USD value) | €25.526cache write €6.381≈ $28.0119 USD (sorted by USD value) | 1M | 49.6Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it. | 38 ±12Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 157.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.7 Inference by Amazon Web Services🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 138.2From 354 benchmarks. Plenty of data behind it. | 118 ±15Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 49.6Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it. | 38 ±12Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 157.5Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.7 Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 138.2From 354 benchmarks. Plenty of data behind it. | 118 ±15Coding IQ 118.2, 95% interval 103–134. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 49.6Fair value (49.6). Costs per task about what its benchmark results predict. Plenty of data behind it. | 38 ±12Terse (38 ±12). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 157.5Epoch 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. | €0.459cache read €0.138≈ $0.5037 USD (sorted by USD value) | €1.836≈ $2.0148 USD (sorted by USD value) | 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 Inference by Aki🇨🇳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. | — | — | 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 Inference by Arkane🇨🇳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. | — | — | 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 Inference by Entrim🇨🇳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. | — | — | 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 Inference by Inceptron🇨🇳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. | — | — | 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 Inference by Mistral 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. | 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. | — | — | 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 Inference by Scaleway🇨🇳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. | — | — | 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 Inference by Sference🇨🇳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. | — | — | 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 Inference by Tensorix🇨🇳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. | — | — | 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. | €0.269cache read €0.067≈ $0.2952 USD (sorted by USD value) | €1.077≈ $1.1819 USD (sorted by USD value) | 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 Inference by Arkane🇨🇳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. | — | — | 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 Inference by Tensorix🇨🇳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. | — | — | 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 |
Claude Opus 4.6 🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 136.9From 466 benchmarks. Plenty of data behind it. | 118 ±5Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | €5.105cache read €0.511≈ $5.6022 USD (sorted by USD value) | €25.526cache write €6.381≈ $28.0119 USD (sorted by USD value) | 1M | 47.2Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 ±15Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 156.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.6 Inference by Amazon Web Services🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 136.9From 466 benchmarks. Plenty of data behind it. | 118 ±5Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 47.2Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 ±15Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 156.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Claude Opus 4.6 Inference by Google🇺🇸Maker headquartered in US, according to the company's own website. The citation is on the model page. Newer version | 136.9From 466 benchmarks. Plenty of data behind it. | 118 ±5Coding IQ 117.9, 95% interval 113–123. Plenty of data behind it. Uses the model's best published results. It has its own scale, separate from llminfo IQ. | — | — | 1M | 47.2Poor value (47.2). Costs more per task than its benchmark results predict. Plenty of data behind it. | 41 ±15Terse (41 ±15). Generates fewer tokens than models with similar coding results. Measured at default effort. A fair amount of data behind it. | 156.3Epoch Capabilities IndexSource: Epoch AI Benchmarking Hub API |
Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence)