Model record

Claude Sonnet 5

max

Anthropic · released Jun 30, 2026

Overall standing

Overall
57.1rank 11 of 63
57.1 is at approximately the 83th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 49.4.
7 of 8 measured · 1 estimated
Category standingsReasoning 69.3Coding 67.1Math 16.9Agentic 28.3
Reasoning
69.3rank 14 of 63
69.3 is at approximately the 79th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 65.0.
3 of 4 measured · 1 estimated
Coding
67.1rank 12 of 63
67.1 is at approximately the 82th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 54.5.
2 of 2 measured
Math
16.9rank 12 of 63
16.9 is at approximately the 81th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.7.
1 of 1 measured
Agentic
28.3rank 12 of 63
28.3 is at approximately the 82th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.0.
1 of 1 measured
Model factsProprietary · $2.0 / $10.0 per 1M

Model facts come from the provider page. Listed API prices carry a separate first-party source and check date.

Provider
Anthropic
Released
Weights
Proprietary
Context window
1,000,000 tokens
Input price / Mtok
$2.0
Output price / Mtok
$10.0
Price source
Official pricing (opens in a new tab)
Reasoning effort
adaptive reasoning, max effort

Scores and sources

Measured scores retain their source and retrieval date. Missing scores are not treated as zero.

Benchmark scores, evaluation settings, sources, and retrieval dates for Claude Sonnet 5
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding80.5Artificial Analysis independent run; 89 tasks; Terminus 2 on E2B; 3 repeats; pass@1; 250-episode cap; 2-hour timeoutOpen source (opens in a new tab)
τ³-BankingAgentic28.3Artificial Analysis independent run; 97 tasks; 5 repeats; backend-state pass@1; BM25 plus grep retrieval; 200-step capOpen source (opens in a new tab)
AA-LCRReasoning70.7Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no toolsOpen source (opens in a new tab)
Humanity's Last ExamReasoning39.6Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no toolsOpen source (opens in a new tab)
GPQA DiamondReasoning91.1Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding53.6Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning—Not measured in this datasetNo source
CritPtMath16.9Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no toolsOpen source (opens in a new tab)