Model comparison
Kimi K3 vs Qwen2.5-Max
Kimi K3 is the stronger model overall, scoring 59.5 to 40.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Kimi K3 scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 25.6.
- Kimi K3 has downloadable open weights; the other is API-only.
Side by side
| Kimi K3 | Qwen2.5-Max | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 59.5 | 40.7 |
| Released | 2026-07-16 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 1.05M | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 53 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1508 | 1359 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), Qwen2.5-Max: —
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| APEX-Agents | 50.6% | — |
| τ²-bench Banking | 37.1% | — |
| PostTrainBench | 32% | — |
| GBAEval | 48.3% | — |
| GDP.pdf | 19% | — |
| Vending-Bench 2 | 5,165 | — |
Reasoning Kimi K3 leads
Kimi K3: 63.0 (#17), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1496 | 1360 |
| Epoch Capabilities Index | 157.45 | 132.53 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| Chess Puzzles | 39% | — |
| LiveBench Reasoning | — | 51.4% |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| ForecastBench | 61.1 | — |
| LiveBench | — | 62.3% |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1491 | 1369 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 97.2% | — |
| ProofBench | 87% | — |
| LiveBench Math | — | 58.4% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1521 | 1337 |
| GPQA Diamond | 93.1% | — |
| SimpleQA Verified | 50.6% | — |
| Confabulations | — | 21.8% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), Qwen2.5-Max: —
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1466 | 1352 |
| LMArena Chinese | 1529 | 1382 |
| LMArena French | 1491 | 1396 |
| LMArena German | 1488 | 1350 |
| LMArena Japanese | 1487 | 1300 |
| LMArena Korean | 1458 | 1304 |
| LMArena Russian | 1482 | 1353 |
| LMArena Spanish | 1472 | 1377 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1483 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Kimi K3 leads
Kimi K3: 45.8 (#29), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1494 | 1358 |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Kimi K3 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1476 | 1367 |
| LMArena Creative Writing | 1454 | 1339 |
| LMArena Multi-Turn | 1488 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 2082 | — |
| EQ-Bench 4 | 1339 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Kimi K3 better than Qwen2.5-Max?
Kimi K3 is the stronger model overall, scoring 59.5 to 40.7 on the Noometry Index.
Is Kimi K3 or Qwen2.5-Max better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 41.8 in the Noometry coding category.
How many benchmarks do Kimi K3 and Qwen2.5-Max share?
18 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and Qwen2.5-Max has 27.