Model intelligence
28 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 | Gemini 3.1 Flash Lite Google· reasoning | 144.4 | 1.05M | $0.25 | Closed | 3 Mar 2026 |
| 2 | Gemini 3.5 Flash Lite Google· reasoning | 145.1 | 1.05M | $0.30 | Closed | 21 Jul 2026 |
| 3 | Inkling Thinking Machines Lab· reasoning | 148.6 | 524K | $1.00 | Open source | 15 Jul 2026 |
| 4 | Inkling Small Thinking Machines Lab· reasoning | 150.1 | 524K | $0.45 | Open source | 15 Jul 2026 |
| 5 | Gemini 3.6 Flash Google· reasoning | 154.4 | 1.05M | $0.75 | Closed | 21 Jul 2026 |
| 6 | Gemini 3.5 Flash Google· reasoning | 154.6 | 1.05M | $1.50 | Closed | 19 May 2026 |
| 7 | Gemini 3.8 Flash Google· reasoning | 157.1 | 1.05M | $0.75 | Closed | 2 Sep 2026 |
| 8 | Gemini 3.7 Flash Google· reasoning | 157.7 | 1.05M | $0.75 | Closed | 13 Aug 2026 |
| 9 | MiMo-V2.6-Pro Xiaomi· reasoning | — | 1.05M | $0.43 | Open source | 21 Sep 2026 |
| 10 | MiMo-V2.6-Flash Xiaomi· reasoning | — | 1.05M | $0.14 | Open source | 21 Sep 2026 |
| 11 | Gemini 3.1 Pro Preview Google· reasoning | — | 1.05M | $2.00 | ? | 19 Feb 2026 |
| 12 | Gemini 2.5 Pro Google· reasoning | — | 1.05M | $1.25 | ? | 17 Jun 2025 |
| 13 | Gemini 3.1 Flash Lite Preview Google· reasoning | — | 1.05M | $0.25 | ? | 3 Mar 2026 |
| 14 | Jev Router | — | 1M | — | ? | 25 Sep 2026 |
| 15 | Perceptron Mk1.5 Perceptron· reasoning | — | 37K | $0.15 | ? | 25 Sep 2026 |
| 16 | Qwen3.8 Omni Flash Alibaba (Qwen)· reasoning | — | 1M | $0.15 | ? | 21 Sep 2026 |
| 17 | MiMo-V2.6-Pro-UltraSpeed Xiaomi· reasoning | — | 1.05M | $4.35 | ? | 21 Sep 2026 |
| 18 | MiMo-V2.5 Xiaomi· reasoning | — | 1.05M | $0.14 | Open source | 22 Apr 2026 |
| 19 | Lyria 3 Pro Preview | — | 1.05M | $0 | ? | 30 Mar 2026 |
| 20 | Lyria 3 Clip Preview | — | 1.05M | $0 | ? | 30 Mar 2026 |
| 21 | Gemini 3.1 Pro Preview Custom Tools Google· reasoning | — | 1.05M | $2.00 | ? | 25 Feb 2026 |
| 22 | GPT Audio | — | 128K | $2.50 | ? | 19 Jan 2026 |
| 23 | GPT Audio Mini | — | 128K | $0.60 | ? | 19 Jan 2026 |
| 24 | Gemini 3 Flash Preview Google· reasoning | — | 1.05M | $0.50 | ? | 17 Dec 2025 |
| 25 | Voxtral Small 24B 2507 | — | 33K | $0.10 | Open source | 30 Oct 2025 |
| 26 | Gemini 2.5 Flash Lite Google· reasoning | — | 1.05M | $0.10 | ? | 22 Jul 2025 |
| 27 | Gemini 2.5 Flash Google· reasoning | — | 1.05M | $0.30 | ? | 17 Jun 2025 |
| 28 | Gemini 2.5 Pro Preview 06-05 Google· reasoning | — | 1.05M | $1.25 | ? | 5 Jun 2025 |
Showing 28 of 28. Benchmark cells are % (best reported setting). 3.8K benchmark results in total.Export CSV