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 | Anthropic: Claude Opus 4.8 | 95.5 |
| 2 | Google: Gemini 2.5 Pro | 94.2 |
| 3 | OpenAI: GPT-5.5 | 93.7 |
| 4 | OpenAI: GPT-5.4 | 90.4 |
| 5 | Z.ai: GLM 5.2 | 89.7 |