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.

#ModelBlended
1Anthropic: Claude Opus 4.895.5
2Google: Gemini 2.5 Pro94.2
3OpenAI: GPT-5.593.7
4OpenAI: GPT-5.490.4
5Z.ai: GLM 5.289.7