Model comparison
Kimi K3 vs QwQ-32B
Kimi K3 is the stronger model overall, scoring 59.5 to 39.8 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Kimi K3 scores higher in 7 categories and QwQ-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Kimi K3 leads 63.0 to 23.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 97.2% for Kimi K3 and 59.2% for QwQ-32B.
Side by side
| Kimi K3 | QwQ-32B | |
|---|---|---|
| Provider | Moonshot AI | Alibaba (Qwen) |
| Noometry Index | 59.5 | 39.8 |
| Released | 2026-07-16 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 1.05M | — |
| Max output | 1.05M | — |
| Input $ / M tokens | $3 | — |
| Output $ / M tokens | $15 | — |
| Results tracked | 53 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Kimi K3 leads
Kimi K3: 61.0 (#10), QwQ-32B: 35.4 (#226)
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1508 | 1333 |
| DeepSWE | 68.5% | — |
| FrontierCode | 44.2% | — |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1654 | — |
| FrontierSWE | 25.9% | — |
| SciCode | 59.5% | — |
| WeirdML | 82.6% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 1,524 | — |
Agentic & Tool Use Not comparable
Kimi K3: 41.8 (#20), QwQ-32B: —
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| 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), QwQ-32B: 23.7 (#174)
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| Chess Puzzles | 39% | 5% |
| LMArena Hard Prompts | 1496 | 1325 |
| Epoch Capabilities Index | 157.45 | 137.6 |
| ForecastBench | 61.1 | 58.3 |
| ARC-AGI-2 | 60.4% | — |
| SimpleBench | 60.7% | — |
| NYT Connections (extended) | 93.6% | — |
| ARC-AGI-1 | 94.5% | — |
| CritPt | 23.4% | — |
| LiveBench Reasoning | — | 83.5% |
| Mystery Game Puzzles | 26% | — |
| DTBench | 91.2% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 52.7% | — |
| Surface Evolver Bench | 95% | — |
| LiveBench | — | 72% |
Math Kimi K3 leads
Kimi K3: 74.2 (#16), QwQ-32B: 38.0 (#143)
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 97.2% | 59.2% |
| LMArena Math | 1491 | 1359 |
| FrontierMath (Tiers 1-3) | 72.2% | — |
| FrontierMath Tier 4 | 39% | — |
| MathArena Final-Answer Competitions | 87.8% | — |
| ProofBench | 87% | — |
| LiveBench Math | — | 77.8% |
Knowledge Kimi K3 leads
Kimi K3: 63.2 (#21), QwQ-32B: 37.2 (#158)
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 93.1% | 65.3% |
| LMArena Expert | 1521 | 1324 |
| SimpleQA Verified | 50.6% | — |
| Confabulations | — | 15.6% |
Multimodal Not comparable
Kimi K3: 37.8 (#70), QwQ-32B: —
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| Blueprint-Bench 2 | 29.5% | — |
| Furniture Assembly | 34.2% | — |
Multilingual Kimi K3 leads
Kimi K3: 56.3 (#21), QwQ-32B: 44.8 (#176)
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1466 | 1305 |
| LMArena Chinese | 1529 | 1378 |
| LMArena French | 1491 | 1336 |
| LMArena German | 1488 | 1313 |
| LMArena Japanese | 1487 | 1262 |
| LMArena Korean | 1458 | 1279 |
| LMArena Russian | 1482 | 1297 |
| LMArena Spanish | 1472 | 1354 |
Instruction Following Kimi K3 leads
Kimi K3: 77.7 (#14), QwQ-32B: 72.6 (#137)
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1483 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
Kimi K3: 45.8 (#29), QwQ-32B: 49.0 (#11)
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1494 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference Kimi K3 leads
Kimi K3: 76.6 (#4), QwQ-32B: 50.6 (#180)
| Benchmark | Kimi K3 | QwQ-32B |
|---|---|---|
| LMArena Text | 1476 | 1329 |
| LMArena Creative Writing | 1454 | 1288 |
| EQ-Bench Creative Writing | 2082 | 1257 |
| LMArena Multi-Turn | 1488 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench 4 | 1339 | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is Kimi K3 better than QwQ-32B?
Kimi K3 is the stronger model overall, scoring 59.5 to 39.8 on the Noometry Index.
Is Kimi K3 or QwQ-32B better for coding?
Kimi K3 scores higher on coding benchmarks: 61.0 versus 35.4 in the Noometry coding category.
How many benchmarks do Kimi K3 and QwQ-32B share?
23 benchmarks have published results for both models. Kimi K3 has 53 scored results on Noometry and QwQ-32B has 36.