Model intelligence
41 AI models
Capability (Epoch Capabilities Index and individual benchmarks from Epoch AI), API list prices and context windows (OpenRouter), release dates and open-weight status. Benchmarks are shown individually - never merged into one invented score.
Epoch Capabilities Index by release date
Capability frontier
Source: Epoch AI (CC BY 4.0). ECI is Epoch's item-response model over many benchmarks; each model page shows its 90% confidence interval.
Blended $/1M tokens (3:1 input:output) vs ECI
Price vs capability
Only models with both an ECI score and an OpenRouter price. Normalisation: 75% input + 25% output price. Click a point to open the model.
| # | Model | ECI ↑ | Context | In $/M | Weights | Released |
|---|---|---|---|---|---|---|
| 1 | DeepSeek V4.1 Flash DeepSeek· reasoning | 155.0 | 1.05M | $0.30 | Open source | 9 Sep 2026 |
| 2 | Qwen3.8 Max (0902) Alibaba (Qwen)· reasoning | 155.3 | 1M | $2.00 | Closed | 1 Sep 2026 |
| 3 | Muse Spark 1.3 Meta· reasoning | 156.9 | 1.05M | $1.25 | Closed | 2 Sep 2026 |
| 4 | Gemini 3.8 Flash Google· reasoning | 157.1 | 1.05M | $0.75 | Closed | 2 Sep 2026 |
| 5 | Claude Fable 5.1 Anthropic· reasoning | 165.0 | 1M | $10.0 | Closed | 1 Sep 2026 |
| 6 | GPT-6 Astra OpenAI· reasoning | 166.6 | 1.05M | $10.0 | Closed | 3 Sep 2026 |
| 7 | Claude Opus 5.5 Anthropic· reasoning | — | 1M | $4.00 | ? | 22 Sep 2026 |
| 8 | Claude Sonnet 5.5 Anthropic· reasoning | — | 1M | $2.00 | ? | 28 Sep 2026 |
| 9 | GPT-6 Sol OpenAI· reasoning | — | 1.05M | $2.00 | ? | 22 Sep 2026 |
| 10 | Grok 4.7 xAI· reasoning | — | 500K | $2.00 | ? | 21 Sep 2026 |
| 11 | MiMo-V2.6-Pro Xiaomi· reasoning | — | 1.05M | $0.43 | Open source | 21 Sep 2026 |
| 12 | MiMo-V2.6-Flash Xiaomi· reasoning | — | 1.05M | $0.14 | Open source | 21 Sep 2026 |
| 13 | GPT-6 Luna OpenAI· reasoning | — | 1.05M | $0.10 | ? | 22 Sep 2026 |
| 14 | Ling 3.0 Flash VL inclusionAI (Ant Group)· reasoning | — | 262K | $0.021 | Open source | 10 Sep 2026 |
| 15 | Mercury 2.5 Inception Labs· reasoning | — | 260K | $0.040 | ? | 8 Sep 2026 |
| 16 | Granite 4.2 8B IBM· reasoning | — | 131K | $0.060 | Open source | 31 Aug 2026 |
| 17 | Jev Router | — | 1M | — | ? | 25 Sep 2026 |
| 18 | Perceptron Mk1.5 Perceptron· reasoning | — | 37K | $0.15 | ? | 25 Sep 2026 |
| 19 | Ember-1 Fireworks AI· reasoning | — | 1.05M | $3.00 | ? | 24 Sep 2026 |
| 20 | GLM 5.3 Prime Z.ai (Zhipu AI)· reasoning | — | 1M | $2.80 | ? | 23 Sep 2026 |
| 21 | Aion 3.5 AionLabs· reasoning | — | 262K | $3.00 | ? | 23 Sep 2026 |
| 22 | Solar Mini 4 Upstage· reasoning | — | 524K | $0.050 | ? | 23 Sep 2026 |
| 23 | Qwen3.8 Max Prime Alibaba (Qwen)· reasoning | — | 1M | $4.00 | ? | 23 Sep 2026 |
| 24 | Aion 3.5 Mini AionLabs· reasoning | — | 262K | $0.70 | ? | 23 Sep 2026 |
| 25 | GPT-6 Sol Pro OpenAI· reasoning | — | 1.05M | $2.00 | ? | 22 Sep 2026 |
| 26 | GPT-6 Luna Pro OpenAI· reasoning | — | 1.05M | $0.10 | ? | 22 Sep 2026 |
| 27 | Qwen3.8 Omni Flash Alibaba (Qwen)· reasoning | — | 1M | $0.15 | ? | 21 Sep 2026 |
| 28 | MiMo-V2.6-Pro-UltraSpeed Xiaomi· reasoning | — | 1.05M | $4.35 | ? | 21 Sep 2026 |
| 29 | GLM 5.3 FlashX Z.ai (Zhipu AI)· reasoning | — | 1.05M | $0.37 | ? | 18 Sep 2026 |
| 30 | Ternary Bonsai 2 27B PrismML· reasoning | — | 262K | $0.075 | Open source | 18 Sep 2026 |
| 31 | Pareto | — | 262K | $2.50 | ? | 17 Sep 2026 |
| 32 | Schematron V2 Turbo | — | 128K | $0.030 | Open source | 12 Sep 2026 |
| 33 | Schematron V2 Small | — | 128K | $0.050 | Open source | 12 Sep 2026 |
| 34 | Fugu Max Sakana AI· reasoning | — | 1M | $2.00 | ? | 11 Sep 2026 |
| 35 | Fugu Ultra v2 Sakana AI· reasoning | — | 1M | $5.00 | ? | 11 Sep 2026 |
| 36 | SWE-2 (max) | — | — | — | Closed | 10 Sep 2026 |
| 37 | Nex-N2.5-Pro Nex AGI· reasoning | — | 262K | $0.075 | Open source | 8 Sep 2026 |
| 38 | Nex-N2.5-Mini Nex AGI· reasoning | — | 262K | $0.025 | Open source | 8 Sep 2026 |
| 39 | GPT-6 Astra Pro OpenAI· reasoning | — | 1.05M | $10.0 | ? | 4 Sep 2026 |
| 40 | GPT-6 Astra (pro, max) | — | — | — | Closed | 3 Sep 2026 |
| 41 | Muse Spark 1.3 Contributor Meta· reasoning | — | 1.05M | $0.10 | ? | 2 Sep 2026 |
Showing 41 of 41. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.Export CSV