VerdictPal
Join

Models / Anthropic

Claude 3 Opus

Claude Opus · Released 2024-03-04

Anthropic's March 2024 Opus. MMLU 86.8%, MMLU-Pro 68.4%, HumanEval baseline on the public ledger.

Pre-Opus-4 historical baseline — not a current pick.

#160 of 168 on AA Index · current snapshot
12 AA Index · 11 benchmark rows · 3 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite34
Context200K
Input / 1M$15
Output / 1M$75
Knowledge cutoff2023-08-01
Statuslightweight
Claude

Family profile

Best published score in each covered benchmark family.

57/100 avg
Knowledge
87
Reasoning
49
Math
64
Coding
28

4 tested benchmark families

Benchmark placements

Where Claude 3 Opus places on each public benchmark source that publishes a row. Rank counts every model with a latest row in the same test — not a universal quality score.

BenchmarkFamilyRankScoreSourceDate
MMLUKnowledge#16/ 2287Anthropic Claude 3 model card2024-03-04
MATHMath#24/ 2564Artificial Analysis2026-09-01
LiveCodeBenchCoding#31/ 3128Artificial Analysis2026-09-01
AIMEMath#37/ 373Artificial Analysis2026-09-01
MMLU-ProKnowledge#39/ 3968MMLU-Pro paper2024-06-03
AA time to first tokenPerformance#88/ 186Artificial Analysis2026-09-01
AA output speedPerformance#89/ 187Artificial Analysis2026-09-01
SciCodeCoding#173/ 18023Artificial Analysis2026-09-01
GPQA DiamondReasoning#179/ 18549Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#180/ 18712Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#180/ 1803Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Claude 3 Opus shows up, it's highlighted.

KnowledgeClaude 3 Opus · 87
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningClaude 3 Opus · 49
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
MathClaude 3 Opus · 64
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    GPT-5 (high)
    99
CodingClaude 3 Opus · 28
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
Newest receipts

Benchmark rows added to the public ledger for Claude 3 Opus in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA output speedPerformance0 t/sArtificial Analysis5
AA time to first tokenPerformance0.00sArtificial Analysis5
AIMEMath3.33%Artificial Analysis5
Artificial Analysis Intelligence IndexReasoning11.8%Artificial Analysis5
GPQA DiamondReasoning48.9%Artificial Analysis5
Humanity's Last ExamReasoning2.8%Artificial Analysis5
LiveCodeBenchCoding27.9%Artificial Analysis5
MATHMath64.07%Artificial Analysis5
SciCodeCoding23.3%Artificial Analysis5
Family coverage

A high composite that hides a weak family is a trap. These bars surface the families where this model hasn't been publicly tested, and where it leads.

Knowledge87
Reasoning49
Math64
Coding28
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover any dot for name, score, and input price. Keyboard: tab through the top twelve, or use the ranking below.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Claude 3 Opus. Scores link to the original source; gaps mean no public row exists yet.

11 sourced rows

11 of 37 catalog benchmarks have a sourced row for Claude 3 Opus.

Knowledge

Reasoning

Math

Coding

Performance

Sources