Model record

Claude Fable 5

max

Anthropic · released Jun 9, 2026

Overall standing

Overall
60.0rank 6 of 62
60.0 is at approximately the 91th 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 69.9Coding 72.4Math 28.6Agentic 26.8
Reasoning
69.9rank 11 of 62
69.9 is at approximately the 83th 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
72.4rank 1 of 46
72.4 is at approximately the 99th 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
28.6rank 4 of 62
28.6 is at approximately the 94th 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
26.8rank 13 of 46
26.8 is at approximately the 72th 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 · $10.0 / $50.0 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
$10.0
Output price / Mtok
$50.0
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 Fable 5
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 timeout; Opus 4.8 fallbackOpen source (opens in a new tab)
τ³-BankingAgentic26.8Artificial Analysis independent run; 97 tasks; 5 repeats; backend-state pass@1; BM25 plus grep retrieval; 200-step cap; Opus 4.8 fallbackOpen source (opens in a new tab)
AA-LCRReasoning70.0Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no tools; Opus 4.8 fallbackOpen source (opens in a new tab)
Humanity's Last ExamReasoning53.3Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no tools; Opus 4.8 fallbackOpen source (opens in a new tab)
GPQA DiamondReasoning92.6Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no tools; Opus 4.8 fallbackOpen source (opens in a new tab)
SciCodeCoding60.2Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1; Opus 4.8 fallbackOpen source (opens in a new tab)
IFBenchReasoning63.5Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1; Opus 4.8 fallbackOpen source (opens in a new tab)
CritPtMath28.6Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no tools; Opus 4.8 fallbackOpen source (opens in a new tab)