MoonshotAI: Kimi K2 0905
Kimi / Moonshot AI
38scores
38benchmarks
$0.4 / $2 per 1M tokenscost in/out
Metadata
Kimi Closed/API
Aliases: kimi-k2-0905, moonshotai-kimi-k2-0905, moonshotai/kimi-k2-0905
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| MCP-Universe | Agentic | 21 | 19.91 | 2026-05-06 |
| MCPMark | Agentic | 21 | 0.22 | 2026-05-06 |
| Tau2 Airline | Agentic | 13 | 0.56 | 2026-05-06 |
| Tau2-Bench Telecom | Agentic | 127 | 73.4% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 131 | 23.5% | 2026-05-11 |
| UAVBench | Agentic | 7 | 77.75 | 2026-05-06 |
| VitaBench | Agentic | 24 | 11.50 | 2026-05-06 |
| OpenUGI | Alignment | 70 | 52.15 | 2026-05-06 |
| ALE-Bench | Coding | 81 | 267.13 | 2026-05-06 |
| MultiPL-E | Coding | 4 | 0.857 | 2026-05-27 |
| SciCode | Coding | 240 | 30.7% | 2026-05-11 |
| TuRTLe Code Completion (Icarus Verilog) | Coding | 9 | 71.77 | 2026-05-06 |
| TuRTLe Code Completion (Verilator) | Coding | 9 | 71.79 | 2026-05-06 |
| TuRTLe Line Completion | Coding | 6 | 33.65 | 2026-05-06 |
| TuRTLe Module Completion (NotSoTiny) | Coding | 6 | 19.00 | 2026-05-06 |
| TuRTLe Spec-to-RTL (Icarus Verilog) | Coding | 9 | 68.72 | 2026-05-06 |
| TuRTLe Spec-to-RTL (Verilator) | Coding | 9 | 67.80 | 2026-05-06 |
| NeoEvalPlusN | Creative | 56 | 16 | 2026-05-06 |
| Vectara HHEM Hallucination Leaderboard | Factuality | 91 | 82.10 | 2026-05-06 |
| MageBench Season 1 | Game | 26 | 1558 rating / 5 games | 2026-05-28 |
| MMLU-Redux | General Knowledge | 13 | 0.93 | 2026-05-06 |
| Artificial Analysis Intelligence Index | Intelligence | 141 | 30.85 | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 233 | 6.3% | 2026-05-11 |
| MMLU-Pro | Intelligence | 79 | 81.9% | 2026-05-11 |
| AIME 2025 | Math | 123 | 57.3% | 2026-05-11 |
| CNMO 2024 | Mathematics | 1 | 0.74 | 2026-05-06 |
| HMMT 2025 | Mathematics | 28 | 0.39 | 2026-05-06 |
| MATH-500 | Mathematics | 6 | 0.97 | 2026-05-06 |
| PolyMath-en | Mathematics | 1 | 0.65 | 2026-05-06 |
| Design Arena | Multimodal | 79 | 1156 | 2026-05-06 |
| Artificial Analysis Openness Index | Openness | 174 | 27.78 | 2026-05-11 |
| AutoLogi | Reasoning | 1 | 0.90 | 2026-05-06 |
| GPQA Diamond | Reasoning | 139 | 76.7% | 2026-05-11 |
| OJBench | Reasoning | 8 | 0.27 | 2026-05-06 |
| EvasionBench | Safety | 5 | 66.68 | 2026-05-06 |
| ChemBench | Science | 17 | 0.60 | 2026-05-06 |
| CritPt | Science | 263 | 0% | 2026-05-11 |
| ACEBench | Tool Use | 1 | 0.77 | 2026-05-06 |
No matching rows.