Model record

Kimi K2.5

reasoningOpen weights

Moonshot AI · released Jan 27, 2026

Overall standing

Overall
45.6rank 41 of 63
45.6 is at approximately the 36th 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 63.2Coding 47.3Math 3.1Agentic 14.2
Reasoning
63.2rank 36 of 63
63.2 is at approximately the 44th 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
47.3rank 44 of 63
47.3 is at approximately the 31th 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
3.1rank 37 of 63
3.1 is at approximately the 40th 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
14.2rank 44 of 63
14.2 is at approximately the 31th 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 factsOpen weights · $0.60 / $3.0 per 1M

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

Provider
Moonshot AI
Released
Weights
Open weights
Context window
262,144 tokens
Input price / Mtok
$0.60
Output price / Mtok
$3.0
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 Kimi K2.5
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding45.7Artificial 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-BankingAgentic14.2Artificial 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-LCRReasoning65.3Artificial 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 ExamReasoning29.4Artificial 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 DiamondReasoning87.9Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding49.0Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning70.2Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath3.1Artificial 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)