VerdictPal
Join

Models / Anthropic

Claude 4 Opus (Reasoning)

Claude 4 · Released 2025-05-22

AA Intelligence Index 31.7. Listed on Artificial Analysis with API pricing $15/$75 per 1M tokens. Benchmark rows sync from the AA snapshot — see the ledger on this page.

Frontier model tracked on Artificial Analysis. Use the benchmark ledger below for sourced scores; we do not infer numbers beyond published rows.

#119 of 166 on AA Index · current snapshot
32 AA Index · 13 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite54
ContextUnlisted
Input / 1M$15
Output / 1M$75
Knowledge cutoffunpublished
Statuslightweight

Family profile

Best published score in each covered benchmark family.

66/100 avg
Knowledge
87
Reasoning
80
Math
98
Coding
64
Agentic
31
Long context
36

6 tested benchmark families

Benchmark placements

Where Claude 4 Opus (Reasoning) 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
MATHMath#6/ 2598Artificial Analysis2026-09-01
MMLU-ProKnowledge#11/ 3987Artificial Analysis2026-09-01
LiveCodeBenchCoding#26/ 3164Artificial Analysis2026-09-01
AIMEMath#30/ 3773Artificial Analysis2026-09-01
AA output speedPerformance#88/ 185Artificial Analysis2026-09-01
AA time to first tokenPerformance#88/ 185Artificial Analysis2026-09-01
IFBenchReasoning#94/ 12754Artificial Analysis2026-09-01
SciCodeCoding#127/ 18040Artificial Analysis2026-09-01
Artificial Analysis Intelligence IndexReasoning#137/ 18432Artificial Analysis2026-09-01
GPQA DiamondReasoning#141/ 18580Artificial Analysis2026-09-01
Humanity's Last ExamReasoning#148/ 18012Artificial Analysis2026-09-01
Terminal-BenchAgentic#149/ 18431Artificial Analysis2026-09-01
AA-LCRLong context#163/ 17936Artificial Analysis2026-09-01
Family context

The three highest-scoring models with pages in each capability family. Where Claude 4 Opus (Reasoning) shows up, it's highlighted.

KnowledgeClaude 4 Opus (Reasoning) · 87
  1. 1
    GPT 5.5
    91
  2. 2
    Claude Opus 4.8
    91
  3. 3
    Claude Sonnet 4.6
    91
ReasoningClaude 4 Opus (Reasoning) · 80
  1. 1
    Claude Mythos Preview
    95
  2. 2
    Gemini 3.7 Flash
    95
  3. 3
    Grok 4.6
    95
MathClaude 4 Opus (Reasoning) · 98
  1. 1
    OpenAI o3
    99
  2. 2
    GPT-5 (medium)
    99
  3. 3
    GPT-5 (high)
    99
CodingClaude 4 Opus (Reasoning) · 64
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticClaude 4 Opus (Reasoning) · 31
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextClaude 4 Opus (Reasoning) · 36
  1. 1
    Muse Spark 1.2
    83
  2. 2
    Kimi K3
    83
  3. 3
    Gemini 3.5 Flash
    81
Newest receipts

Benchmark rows added to the public ledger for Claude 4 Opus (Reasoning) in the last 120 days. Older rows live in the full table below.

13 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context36.33%Artificial Analysis2
AA output speedPerformance0 t/sArtificial Analysis2
AA time to first tokenPerformance0.00sArtificial Analysis2
AIMEMath73.33%Artificial Analysis2
Artificial Analysis Intelligence IndexReasoning31.7%Artificial Analysis2
GPQA DiamondReasoning79.6%Artificial Analysis2
Humanity's Last ExamReasoning12.3%Artificial Analysis2
IFBenchReasoning53.74%Artificial Analysis2
LiveCodeBenchCoding63.6%Artificial Analysis2
MATHMath98.2%Artificial Analysis2
MMLU-ProKnowledge87.3%Artificial Analysis2
SciCodeCoding39.8%Artificial Analysis2
Terminal-BenchAgentic31.06%Artificial Analysis2
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
Reasoning80
Math98
Coding64
Agentic31
Long context36
Price vs. performance
0255075100$0.10$0.30$1$3$10$30input USD / 1M tokens · log scale →← intelligence

Hover or tab any dot for name, score, and input price.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaMiniMaxxAIZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Claude 4 Opus (Reasoning). Scores link to the original source; gaps mean no public row exists yet.

13 sourced rows

13 of 37 catalog benchmarks have a sourced row for Claude 4 Opus (Reasoning).

Knowledge

Reasoning

Math

Coding

Agentic

Long context

Performance

Sources