priorsBuilder

Anthropic · released 2024-03-04

Opus 3

Measured on 11 benchmarks.

General frontier

Not ranked in this mix — too little measured data for its benchmarks.

Your mix’s benchmarks

2 of 8 measured

reasoning

Humanity's Last Exam

587 results
  1. #583none of 5872.8%

Leader: Opus 5.5 · 61.4%

reasoning

SimpleBench

97 results
  1. #85none of 9723.5%

Leader: Opus 5.5 · 88.4%

All 11 benchmarks

show 9 more

coding

LiveCodeBench

282 results
  1. #195none of 28227.9%

Leader: Gemini 3 Pro · 91.7%

composite

AA Intelligence Index v4.3.2

610 results
  1. #416none of 6108.7

Leader: Opus 5.5 · 57.6

composite

Arena Text

220 results
  1. #172none of 2201322

Leader: Gemini 4 · 1525

composite

Arena Text — Multi-Turn

220 results
  1. #170none of 2201322

Leader: Gemini 4 · 1553

knowledge

GPQA Diamond

539 results
  1. #420none of 53948.9%

Leader: GPT-6 Astra · 96.3%

knowledge

MMLU-Pro

285 results
  1. #182none of 28569.6%

Leader: Gemini 3 Pro · 89.8%

math

MATH-500

162 results
  1. #125none of 16264.1%

Leader: GPT-5 · 99.4%

other

Arena Vision

116 results
  1. #111none of 1161061

Leader: Fable 5 · 1308

other

T3 Code usage share

85 results
  1. #68none of 850.0%

Leader: Opus 5.5 · 29.1%