Model record

Claude Haiku 4.5

reasoning

Anthropic · released Oct 15, 2025

Overall standing

Overall
37.3rank 54 of 63
37.3 is at approximately the 15th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 49.4.
8 of 8 measured
Category standingsReasoning 50.4Coding 43.7Math 0.0Agentic 9.1
Reasoning
50.4rank 55 of 63
50.4 is at approximately the 13th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 65.0.
4 of 4 measured
Coding
43.7rank 51 of 63
43.7 is at approximately the 20th 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
0.0rank 54 of 63
0.0 is at approximately the 8th 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
9.1rank 59 of 63
9.1 is at approximately the 7th 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 · $1.0 / $5.0 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
200,000 tokens
Input price / Mtok
$1.0
Output price / Mtok
$5.0
Price source
Official pricing (opens in a new tab)
Reasoning effort
reasoning

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 Haiku 4.5
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding44.2Artificial 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-BankingAgentic9.1Artificial 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-LCRReasoning70.3Artificial 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 ExamReasoning9.7Artificial 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 DiamondReasoning67.2Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding43.3Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning54.3Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath0.0Artificial 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)