Model record

Claude Opus 4.8

max

Anthropic · released May 28, 2026

Overall standing

Overall
56.8rank 13 of 62
56.8 is at approximately the 80th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 48.9.
8 of 8 measured
Category standingsReasoning 66.9Coding 69.1Math 20.9Agentic 27.6
Reasoning
66.9rank 23 of 62
66.9 is at approximately the 64th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 64.8.
4 of 4 measured
Coding
69.1rank 7 of 46
69.1 is at approximately the 86th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 56.1.
2 of 2 measured
Math
20.9rank 8 of 62
20.9 is at approximately the 87th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.3.
1 of 1 measured
Agentic
27.6rank 11 of 46
27.6 is at approximately the 77th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.6.
1 of 1 measured
Model factsClosed weights · $5.0 / $25.0 per 1M

Copied from the linked provider page; no separate retrieval date is stored.

Provider
Anthropic
Released
Weights
Closed weights
Context window
1,000,000 tokens
Input price / Mtok
$5.0
Output price / Mtok
$25.0
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 Opus 4.8
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding84.6Artificial 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-BankingAgentic27.6Artificial 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-LCRReasoning67.7Artificial 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 ExamReasoning45.7Artificial 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 DiamondReasoning92.0Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding53.5Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning62.2Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath20.9Artificial 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)