Model comparison
Kimi K2 (Jul 2025) vs Qwen2.5-Max
Kimi K2 (Jul 2025) and Qwen2.5-Max score almost the same on the Noometry Index (41.2 vs 40.7), so choose on price, context window or the category you care about most.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Kimi K2 (Jul 2025) scores higher in 5 categories and Qwen2.5-Max in 3 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Kimi K2 (Jul 2025) leads 62.3 to 55.4.
- The biggest single-benchmark swing is Short-Story Creative Writing: 85.6% for Kimi K2 (Jul 2025) and 72.9% for Qwen2.5-Max.
- Kimi K2 (Jul 2025) has downloadable open weights; the other is API-only.
Side by side
| Kimi K2 (Jul 2025) | Qwen2.5-Max | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 41.2 | 40.7 |
| Released | 2025-07-12 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.57 | — |
| Output $ / M tokens | $2.30 | — |
| Results tracked | 42 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Kimi K2 (Jul 2025): 42.4 (#102), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1399 | 1359 |
| SWE-bench Verified (bash only) | 63.4% | — |
| Aider Polyglot | 59.1% | — |
| GSO | 4.9% | — |
| WeirdML | 42.8% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 597.5 | — |
Agentic & Tool Use Not comparable
Kimi K2 (Jul 2025): 32.4 (#64), Qwen2.5-Max: —
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| Terminal-Bench | 35.7% | — |
| Berkeley Function Calling Leaderboard | 59.1% | — |
| METR Time Horizons | 59.2% | — |
Reasoning Qwen2.5-Max leads
Kimi K2 (Jul 2025): 23.3 (#179), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1384 | 1360 |
| Epoch Capabilities Index | 146.01 | 132.53 |
| SimpleBench | 26.3% | — |
| Kagi LLM Benchmark | 64.4% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| ForecastBench | 60.2 | — |
| LiveBench | — | 62.3% |
Math Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 42.7 (#83), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1397 | 1369 |
| Omni-MATH | 65.4% | — |
| LiveBench Math | — | 58.4% |
| FrontierMath (Feb 2025 set) | 21.4% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 37.3 (#157), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| Confabulations | 20.4% | 21.8% |
| LMArena Expert | 1365 | 1337 |
| MMLU-Pro | 81.9% | — |
| Vectara Hallucination Rate | 17.9% | — |
| GPQA (HELM) | 65.3% | — |
Multilingual Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 49.6 (#130), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1372 | 1352 |
| LMArena Chinese | 1415 | 1382 |
| LMArena French | 1379 | 1396 |
| LMArena German | 1387 | 1350 |
| LMArena Japanese | 1349 | 1300 |
| LMArena Korean | 1325 | 1304 |
| LMArena Russian | 1385 | 1353 |
| LMArena Spanish | 1386 | 1377 |
Instruction Following Too close to call
Kimi K2 (Jul 2025): 71.1 (#156), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1348 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
| IFEval | 85% | — |
Long Context Too close to call
Kimi K2 (Jul 2025): 41.2 (#145), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1353 | 1358 |
| Fiction.LiveBench | 66.7% | — |
| CL-bench | 17.6% | — |
Writing & Preference Kimi K2 (Jul 2025) leads
Kimi K2 (Jul 2025): 62.3 (#78), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Kimi K2 (Jul 2025) | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1380 | 1367 |
| LMArena Creative Writing | 1350 | 1339 |
| Short-Story Creative Writing | 85.6% | 72.9% |
| LMArena Multi-Turn | 1371 | 1364 |
| EQ-Bench Creative Writing | 1666 | — |
| WildBench | 86.2% | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Kimi K2 (Jul 2025) better than Qwen2.5-Max?
Kimi K2 (Jul 2025) and Qwen2.5-Max score almost the same on the Noometry Index (41.2 vs 40.7), so choose on price, context window or the category you care about most.
Is Kimi K2 (Jul 2025) or Qwen2.5-Max better for coding?
They score almost the same on coding (42.4 vs 41.8); test both on your own repository before choosing.
How many benchmarks do Kimi K2 (Jul 2025) and Qwen2.5-Max share?
20 benchmarks have published results for both models. Kimi K2 (Jul 2025) has 42 scored results on Noometry and Qwen2.5-Max has 27.