Model comparison
MiniMax-M2 vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 37.4 on the Noometry Index.
Last verified . 15 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. MiniMax-M2 scores higher in 3 categories and QwQ-32B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where QwQ-32B leads 49.0 to 40.5.
Side by side
| MiniMax-M2 | QwQ-32B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 39.8 |
| Released | 2025-10-27 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 21 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.3 (#159), QwQ-32B: 35.4 (#226)
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1370 | 1333 |
| SWE-bench Verified (bash only) | 61% | — |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1297 | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
Agentic & Tool Use Not comparable
MiniMax-M2: 25.1 (#109), QwQ-32B: —
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning QwQ-32B leads
MiniMax-M2: 19.4 (#258), QwQ-32B: 23.7 (#174)
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1325 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| Epoch Capabilities Index | — | 137.6 |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math Too close to call
MiniMax-M2: 37.3 (#160), QwQ-32B: 38.0 (#143)
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| LMArena Math | 1352 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| LiveBench Math | — | 77.8% |
Knowledge Too close to call
MiniMax-M2: 37.0 (#163), QwQ-32B: 37.2 (#158)
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| LMArena Expert | 1337 | 1324 |
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
Multilingual Too close to call
MiniMax-M2: 45.3 (#171), QwQ-32B: 44.8 (#176)
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1313 | 1305 |
| LMArena Chinese | 1366 | 1378 |
| LMArena French | 1335 | 1336 |
| LMArena German | 1355 | 1313 |
| LMArena Russian | 1331 | 1297 |
| LMArena Spanish | 1326 | 1354 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1279 |
Instruction Following QwQ-32B leads
MiniMax-M2: 70.2 (#166), QwQ-32B: 72.6 (#137)
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1328 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
MiniMax-M2: 40.5 (#153), QwQ-32B: 49.0 (#11)
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1331 | 1308 |
| Fiction.LiveBench | — | 83.3% |
Writing & Preference MiniMax-M2 leads
MiniMax-M2: 53.0 (#162), QwQ-32B: 50.6 (#180)
| Benchmark | MiniMax-M2 | QwQ-32B |
|---|---|---|
| LMArena Text | 1340 | 1329 |
| LMArena Creative Writing | 1286 | 1288 |
| LMArena Multi-Turn | 1361 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| EQ-Bench Creative Writing | — | 1257 |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is MiniMax-M2 better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 37.4 on the Noometry Index.
Is MiniMax-M2 or QwQ-32B better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 35.4 in the Noometry coding category.
How many benchmarks do MiniMax-M2 and QwQ-32B share?
15 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and QwQ-32B has 36.