Codesota · Models · Claude 3 OpusAnthropic4 results · 4 benchmarks
Model card

Claude 3 Opus.

AnthropicapiLLM

Anthropic's Claude 3 Opus model.

§ 02 · Benchmarks

Every benchmark Claude 3 Opus has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01HumanEvalCode & Software Engineering · Code Generationpass@184.9%#26/332026-04-20source ↗
02MATHLanguage & Knowledge · Mathematical Reasoningaccuracy60.1%#29/292026-04-20unverified
03MMLU—accuracy86.8%#12/192026-04-20unverified
04GPQA—accuracy50.4%#12/172026-04-20unverified
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Claude 3 Opus actually performs.

Code & Software Engineering
1
benchmark
avg rank #26.0
Language & Knowledge
1
benchmark
avg rank #29.0
§ 06 · Sources & freshness

Where these numbers come from.

src
3
results
codesota-api
1
result
0 of 4 rows marked verified.