VerdictPal
Join

Models / Anthropic

Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)

Claude Opus · Released 2026-07-24

AA Intelligence Index 60.1. Listed on Artificial Analysis with API pricing $5/$25 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.

#1 of 184 on AA Index · current snapshot
50 AA Index · 9 benchmark rows · 1 sourcesPosition is benchmark-specific — not a cross-family or cross-source ranking.
Composite66
Context128K
Input / 1M$5.0
Output / 1M$25
Knowledge cutoffopen
Output speed54 t/s
TTFT (default API)21.73s
Statussolid

Family profile

Best published score in each covered benchmark family.

80/100 avg
Reasoning
94
Coding
56
Agentic
88
Long context
80

4 tested benchmark families

Benchmark placements

Where Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) 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
Artificial Analysis Intelligence IndexReasoning#5/ 18850Artificial Analysis2026-09-10
Humanity's Last ExamReasoning#5/ 18554Artificial Analysis2026-09-10
Terminal-BenchAgentic#5/ 18988Artificial Analysis2026-09-10
GPQA DiamondReasoning#10/ 19094Artificial Analysis2026-09-10
AA time to first tokenPerformance#13/ 190Artificial Analysis2026-09-10
τ³-Bench BankingAgentic#14/ 11143Artificial Analysis2026-09-10
SciCodeCoding#17/ 9456Artificial Analysis2026-09-10
AA-LCRLong context#30/ 18280Artificial Analysis2026-09-10
AA output speedPerformance#70/ 190Artificial Analysis2026-09-10
Family context

The three highest-scoring models with pages in each capability family. Where Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) shows up, it's highlighted.

ReasoningClaude Opus 5 (Adaptive Reasoning, Xhigh Effort) · 94
  1. 1
    GPT-6 Astra
    96
  2. 2
    Claude Mythos Preview
    95
  3. 3
    Gemini 3.7 Flash
    95
CodingClaude Opus 5 (Adaptive Reasoning, Xhigh Effort) · 56
  1. 1
    GPT 5.5
    96
  2. 2
    Claude Opus 4.8
    96
  3. 3
    Claude Opus 4.6
    96
AgenticClaude Opus 5 (Adaptive Reasoning, Xhigh Effort) · 88
  1. 1
    GPT 5.5
    100
  2. 2
    Claude Opus 4.8
    100
  3. 3
    Claude Fable 5
    100
Long contextClaude Opus 5 (Adaptive Reasoning, Xhigh Effort) · 80
  1. 1
    Kimi K3
    89
  2. 2
    Claude Fable 5.1
    85
  3. 3
    GPT-5.5 (high)
    84
Newest receipts

Benchmark rows added to the public ledger for Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) in the last 120 days. Older rows live in the full table below.

9 recent
BenchmarkFamilyScoreSourceDays ago
AA-LCRLong context80.33%Artificial Analysis4
AA output speedPerformance54 t/sArtificial Analysis4
AA time to first tokenPerformance21.73sArtificial Analysis4
Artificial Analysis Intelligence IndexReasoning49.7%Artificial Analysis4
GPQA DiamondReasoning93.7%Artificial Analysis4
Humanity's Last ExamReasoning54.4%Artificial Analysis4
SciCodeCoding55.7%Artificial Analysis4
τ³-Bench BankingAgentic43.3%Artificial Analysis4
Terminal-BenchAgentic88.01%Artificial Analysis4
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.

Reasoning94
Coding56
Agentic88
Long context80
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.

AnthropicOpenAIMistralAlibabaDeepSeekGoogleMoonshotMetaxAIMiniMaxZhipuXiaomiOtherMeituanCohereNVIDIA

Full benchmark ledger

Every catalog benchmark for Claude Opus 5 (Adaptive Reasoning, Xhigh Effort). Scores link to the original source; gaps mean no public row exists yet.

9 sourced rows

9 of 37 catalog benchmarks have a sourced row for Claude Opus 5 (Adaptive Reasoning, Xhigh Effort).

Reasoning

Coding

Agentic

Long context

Performance

Sources