Model comparison
Kimi K2.7 Code vs Qwen2.5 72B Instruct
Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 31.5 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. Kimi K2.7 Code scores higher in 5 categories and Qwen2.5 72B Instruct in 0 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Kimi K2.7 Code leads 52.6 to 18.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 95.6% for Kimi K2.7 Code and 8.1% for Qwen2.5 72B Instruct.
- Kimi K2.7 Code is cheaper at $0.95 / $4 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- Kimi K2.7 Code accepts more context: 262K tokens versus 131K.
Side by side
| Kimi K2.7 Code | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 43.0 | 31.5 |
| Released | 2026-06-12 | 2024-09 |
| Weights | Open | Open |
| Context window | 262K | 131K |
| Max output | 262K | 8K |
| Input $ / M tokens | $0.95 | $1.40 |
| Output $ / M tokens | $4 | $5.60 |
| Results tracked | 19 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K2.7 Code leads
Kimi K2.7 Code: 42.4 (#92), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 54.1% | 16% |
| DeepSWE | 30.5% | — |
| FrontierCode | 30.1% | — |
| LMArena WebDev | 1473 | — |
| SciCode | 47.5% | — |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1293 |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 886.23 | — |
Agentic & Tool Use Kimi K2.7 Code leads
Kimi K2.7 Code: 23.9 (#115), Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| APEX-Agents | 37.6% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| GBAEval | 0.9% | — |
| METR Time Horizons | — | 35.8% |
| Vending-Bench 2 | 5,083 | — |
Reasoning Kimi K2.7 Code leads
Kimi K2.7 Code: 38.2 (#56), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| Epoch Capabilities Index | 150.01 | 129.01 |
| SimpleBench | 57.9% | — |
| CritPt | 10% | — |
| Chess Puzzles | 21% | — |
| LMArena Hard Prompts | — | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| Surface Evolver Bench | 48.8% | — |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math Kimi K2.7 Code leads
Kimi K2.7 Code: 52.6 (#39), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 95.6% | 8.1% |
| FrontierMath (Tiers 1-3) | 54% | — |
| FrontierMath Tier 4 | 12.2% | — |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
Knowledge Kimi K2.7 Code leads
Kimi K2.7 Code: 53.6 (#51), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 87.9% | 49.1% |
| SimpleQA Verified | 36.5% | — |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Not comparable
Kimi K2.7 Code: —, Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1255 |
Instruction Following Not comparable
Kimi K2.7 Code: —, Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |
Long Context Not comparable
Kimi K2.7 Code: —, Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |
Writing & Preference Not comparable
Kimi K2.7 Code: —, Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | Kimi K2.7 Code | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |
Frequently asked questions
Is Kimi K2.7 Code better than Qwen2.5 72B Instruct?
Kimi K2.7 Code is the stronger model overall, scoring 43.0 to 31.5 on the Noometry Index.
Which is cheaper, Kimi K2.7 Code or Qwen2.5 72B Instruct?
Kimi K2.7 Code is cheaper. It lists at $0.95 per million input tokens and $4 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is Kimi K2.7 Code or Qwen2.5 72B Instruct better for coding?
Kimi K2.7 Code scores higher on coding benchmarks: 42.4 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
Kimi K2.7 Code does, with 262K tokens against 131K.
How many benchmarks do Kimi K2.7 Code and Qwen2.5 72B Instruct share?
4 benchmarks have published results for both models. Kimi K2.7 Code has 19 scored results on Noometry and Qwen2.5 72B Instruct has 43.