benchmarks
Top Models by Benchmark Score (2026)
Ranked by blended benchmark data from Aider Polyglot and Artificial Analysis Intelligence Index. Available models only - any under access restrictions are excluded.
| # | Model | Blended |
|---|---|---|
| 1 | OpenAI: GPT-5.6 Sol (batch) | 99.3 |
| 2 | OpenAI: GPT-5.6 Sol | 99.3 |
| 3 | Anthropic: Claude Fable 5 (batch) | 99.2 |
| 4 | Anthropic: Claude Fable 5 | 99.2 |
| 5 | Google: Gemini 2.5 Pro | 94.2 |