Model comparison
MiniMax-M2.5 vs QwQ-32B
QwQ-32B is the stronger model overall, scoring 39.8 to 38.3 on the Noometry Index.
Last verified . 19 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 19 benchmarks with published results for both. MiniMax-M2.5 scores higher in 4 categories and QwQ-32B in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 35.4.
Side by side
| MiniMax-M2.5 | QwQ-32B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.3 | 39.8 |
| Released | 2026-02-12 | 2024-11-28 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 48.1 (#58), QwQ-32B: 35.4 (#226)
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| LMArena Coding | 1381 | 1333 |
| SWE-bench Verified (bash only) | 75.8% | — |
| Aider Polyglot | — | 20.9% |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| BigCodeBench Instruct | — | 44.6% |
| LiveBench Coding | — | 72.2% |
| BigCodeBench Complete | — | 54.4% |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), QwQ-32B: —
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning QwQ-32B leads
MiniMax-M2.5: 17.5 (#292), QwQ-32B: 23.7 (#174)
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1325 |
| Epoch Capabilities Index | 146.68 | 137.6 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | — | 5% |
| LiveBench Reasoning | — | 83.5% |
| LiveBench Data Analysis | — | 65% |
| ForecastBench | — | 58.3 |
| LiveBench | — | 72% |
Math QwQ-32B leads
MiniMax-M2.5: 26.9 (#253), QwQ-32B: 38.0 (#143)
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| LMArena Math | 1378 | 1359 |
| OTIS Mock AIME 2024-2025 | — | 59.2% |
| ProofBench | 4% | — |
| LiveBench Math | — | 77.8% |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), QwQ-32B: 37.2 (#158)
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| LMArena Expert | 1379 | 1324 |
| GPQA Diamond | — | 65.3% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | 9.1% | — |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.1 (#152), QwQ-32B: 44.8 (#176)
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| LMArena Non-English | 1338 | 1305 |
| LMArena Chinese | 1393 | 1378 |
| LMArena French | 1362 | 1336 |
| LMArena German | 1362 | 1313 |
| LMArena Japanese | 1171 | 1262 |
| LMArena Korean | 1232 | 1279 |
| LMArena Russian | 1358 | 1297 |
| LMArena Spanish | 1354 | 1354 |
Instruction Following QwQ-32B leads
MiniMax-M2.5: 71.5 (#148), QwQ-32B: 72.6 (#137)
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| LMArena Instruction Following | 1353 | 1297 |
| LiveBench Instruction Following | — | 81.8% |
Long Context QwQ-32B leads
MiniMax-M2.5: 37.5 (#216), QwQ-32B: 49.0 (#11)
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| LMArena Longer Query | 1366 | 1308 |
| Fiction.LiveBench | — | 83.3% |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 53.9 (#153), QwQ-32B: 50.6 (#180)
| Benchmark | MiniMax-M2.5 | QwQ-32B |
|---|---|---|
| LMArena Text | 1359 | 1329 |
| LMArena Creative Writing | 1331 | 1288 |
| EQ-Bench Creative Writing | 1361 | 1257 |
| LMArena Multi-Turn | 1364 | 1314 |
| Short-Story Creative Writing | — | 80.2% |
| LiveBench Language | — | 51.4% |
Frequently asked questions
Is MiniMax-M2.5 better than QwQ-32B?
QwQ-32B is the stronger model overall, scoring 39.8 to 38.3 on the Noometry Index.
Is MiniMax-M2.5 or QwQ-32B better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 35.4 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and QwQ-32B share?
19 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and QwQ-32B has 36.