Model record
Kimi K2 Thinking
Open weightsMoonshot AI · released Nov 6, 2025
Overall standing
- Overall
- 44.5rank 45 of 63
- 44.5 is at approximately the 29th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 49.4.
- 6 of 8 measured · 2 estimated
Category standingsReasoning 60.2Coding 48.7Math 2.6Agentic 15.7
- Reasoning
- 60.2rank 44 of 63
- 60.2 is at approximately the 31th 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
- 48.7rank 41 of 63
- 48.7 is at approximately the 36th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 54.5.
- 1 of 2 measured · 1 estimated
- Math
- 2.6rank 43 of 63
- 2.6 is at approximately the 32th 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
- 15.7rank 41 of 63
- 15.7 is at approximately the 36th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.0.
- 0 of 1 measured · 1 estimated
Model factsOpen weights · Price not listed
Model facts come from the provider page. Listed API prices carry a separate first-party source and check date.
Scores and sources
Measured scores retain their source and retrieval date. Missing scores are not treated as zero.
| Benchmark | Category | Score | Evaluation settings | Source |
|---|---|---|---|---|
| Terminal-Bench v2.1 | Coding | — | Not measured in this dataset | No source |
| τ³-Banking | Agentic | — | Not measured in this dataset | No source |
| AA-LCR | Reasoning | 66.3 | Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no tools | Open source (opens in a new tab) |
| Humanity's Last Exam | Reasoning | 22.3 | Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no tools | Open source (opens in a new tab) |
| GPQA Diamond | Reasoning | 83.8 | Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no tools | Open source (opens in a new tab) |
| SciCode | Coding | 42.4 | Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1 | Open source (opens in a new tab) |
| IFBench | Reasoning | 68.1 | Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1 | Open source (opens in a new tab) |
| CritPt | Math | 2.6 | Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no tools | Open source (opens in a new tab) |