picksbymodel Get API access →
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 5.5 (batch)100.0
2Anthropic: Claude Opus 5.5100.0
3Google: Gemini 2.5 Pro94.2
4Google: Gemini 2.5 Pro (batch)94.2
5Anthropic: Claude Fable 5.1 (batch)92.0

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.