benchmarks
Top Models by Benchmark Score (2026)
Ranked by blended benchmark data from Aider Polyglot and Artificial Analysis Intelligence Index.
| # | Model | Blended |
|---|---|---|
| 1 | Anthropic: Claude Fable 5 | 99.7 |
| 2 | OpenAI: GPT-5.5 | 96.6 |
| 3 | Anthropic: Claude Opus 4.8 | 96.5 |
| 4 | OpenAI: GPT-5.4 | 94.2 |
| 5 | Google: Gemini 2.5 Pro | 94.2 |