Model comparison
MiniMax-M3 vs QwQ-32B
MiniMax-M3 is the stronger model overall, scoring 43.8 to 39.8 on the Noometry Index.
Last verified . 22 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 22 benchmarks with published results for both. MiniMax-M3 scores higher in 7 categories and QwQ-32B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 37.2.
- The biggest single-benchmark swing is GPQA Diamond: 90.9% for MiniMax-M3 and 65.3% for QwQ-32B.
Side by side
| MiniMax-M3 | QwQ-32B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.8 | 39.8 |
| Released | 2026-06-01 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 512K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 41 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), QwQ-32B: 35.4 (#226)
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1469 | 1333 |
| FrontierCode | 14.7% | — |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), QwQ-32B: —
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 30.1 (#87), QwQ-32B: 23.7 (#174)
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| Chess Puzzles | 14% | 5% |
| LMArena Hard Prompts | 1447 | 1325 |
| Epoch Capabilities Index | 146.95 | 137.6 |
| ForecastBench | 61.4 | 58.3 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| LiveBench Reasoning | — | 83.5% |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LiveBench Data Analysis | — | 65% |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| LiveBench | — | 72% |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), QwQ-32B: 38.0 (#143)
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 59.2% |
| LMArena Math | 1429 | 1359 |
| ProofBench | 18% | — |
| LiveBench Math | — | 77.8% |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), QwQ-32B: 37.2 (#158)
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| GPQA Diamond | 90.9% | 65.3% |
| LMArena Expert | 1461 | 1324 |
| Confabulations | — | 15.6% |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), QwQ-32B: —
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), QwQ-32B: 44.8 (#176)
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1420 | 1305 |
| LMArena Chinese | 1463 | 1378 |
| LMArena French | 1447 | 1336 |
| LMArena German | 1426 | 1313 |
| LMArena Japanese | 1381 | 1262 |
| LMArena Korean | 1372 | 1279 |
| LMArena Russian | 1428 | 1297 |
| LMArena Spanish | 1432 | 1354 |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), QwQ-32B: 72.6 (#137)
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
MiniMax-M3: 44.2 (#72), QwQ-32B: 49.0 (#11)
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1445 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), QwQ-32B: 50.6 (#180)
| Benchmark | MiniMax-M3 | QwQ-32B |
|---|---|---|
| LMArena Text | 1433 | 1329 |
| LMArena Creative Writing | 1404 | 1288 |
| LMArena Multi-Turn | 1442 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| EQ-Bench 4 | 1150 | — |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is MiniMax-M3 better than QwQ-32B?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 39.8 on the Noometry Index.
Is MiniMax-M3 or QwQ-32B better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 35.4 in the Noometry coding category.
How many benchmarks do MiniMax-M3 and QwQ-32B share?
22 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and QwQ-32B has 36.