Model comparison
MiniMax-M2.5 vs Qwen2.5-Max
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 38.3 on the Noometry Index.
Last verified . 18 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. MiniMax-M2.5 scores higher in 3 categories and Qwen2.5-Max in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 36.9 to 26.9.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.5 | Qwen2.5-Max | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.3 | 40.7 |
| Released | 2026-02-12 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 27 |
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), Qwen2.5-Max: 41.8 (#117)
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1381 | 1359 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), Qwen2.5-Max: —
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Qwen2.5-Max leads
MiniMax-M2.5: 17.5 (#292), Qwen2.5-Max: 25.6 (#147)
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1360 |
| Epoch Capabilities Index | 146.68 | 132.53 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
MiniMax-M2.5: 26.9 (#253), Qwen2.5-Max: 36.9 (#162)
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1378 | 1369 |
| ProofBench | 4% | — |
| LiveBench Math | — | 58.4% |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), Qwen2.5-Max: 35.3 (#186)
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1379 | 1337 |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 9.1% | — |
Multilingual Qwen2.5-Max leads
MiniMax-M2.5: 47.1 (#152), Qwen2.5-Max: 48.1 (#146)
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1338 | 1352 |
| LMArena Chinese | 1393 | 1382 |
| LMArena French | 1362 | 1396 |
| LMArena German | 1362 | 1350 |
| LMArena Japanese | 1171 | 1300 |
| LMArena Korean | 1232 | 1304 |
| LMArena Russian | 1358 | 1353 |
| LMArena Spanish | 1354 | 1377 |
Instruction Following Too close to call
MiniMax-M2.5: 71.5 (#148), Qwen2.5-Max: 71.3 (#152)
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1353 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Qwen2.5-Max leads
MiniMax-M2.5: 37.5 (#216), Qwen2.5-Max: 41.4 (#142)
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1366 | 1358 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference Qwen2.5-Max leads
MiniMax-M2.5: 53.9 (#153), Qwen2.5-Max: 55.4 (#146)
| Benchmark | MiniMax-M2.5 | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1359 | 1367 |
| LMArena Creative Writing | 1331 | 1339 |
| LMArena Multi-Turn | 1364 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1361 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is MiniMax-M2.5 better than Qwen2.5-Max?
Qwen2.5-Max is the stronger model overall, scoring 40.7 to 38.3 on the Noometry Index.
Is MiniMax-M2.5 or Qwen2.5-Max better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 41.8 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and Qwen2.5-Max share?
18 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen2.5-Max has 27.