Claude 3 Opus (20240229) — benchmark results

February 29, 2024 Claude 3 Opus snapshot, tracked separately from generic Claude 3 Opus rows. Provider: Anthropic. Released 2024-02-29. Access: API.

Unified ELO 1578 ± 16, rank #538 of 1776 rated models, from 107 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
HELM EWoK - Agent Properties94.46EM100
HELM Finance - FinanceBench70Correct Answer100
LiveBench Typos68Score100
LogicKor - Grammar9.64Score (0-10)100
LiveBench Plot Unscrambling50.16Score98.6
LiveBench Table Join40.96Score98.6
LogicKor - Writing9.78Score (0-10)98.2
HELM ThaiExam - IC76.84EM97.6
HELM ThaiExam - ONET66.67EM97.6
HELM ThaiExam - TGAT80EM97.6
HELM ThaiExam - ThaiExam68.57EM97.6
LogicKor - Coding9.85Score (0-10)97.6

Interactive version: theaggregate.ai/model?slug=claude-3-opus-20240229 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.