Model comparison
MiniMax-M2.5 vs Qwen3.5 Max Preview
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 38.3 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M2.5 scores higher in 1 category and Qwen3.5 Max Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Max Preview leads 30.8 to 17.5.
- MiniMax-M2.5 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.5 | Qwen3.5 Max Preview | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.3 | 45.3 |
| Released | 2026-02-12 | — |
| Weights | Open | Proprietary |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 17 |
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), Qwen3.5 Max Preview: 44.0 (#77)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Coding | 1381 | 1487 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), Qwen3.5 Max Preview: —
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Qwen3.5 Max Preview leads
MiniMax-M2.5: 17.5 (#292), Qwen3.5 Max Preview: 30.8 (#84)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1483 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Epoch Capabilities Index | 146.68 | — |
Math Qwen3.5 Max Preview leads
MiniMax-M2.5: 26.9 (#253), Qwen3.5 Max Preview: 40.1 (#94)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Math | 1378 | 1474 |
| ProofBench | 4% | — |
Knowledge Qwen3.5 Max Preview leads
MiniMax-M2.5: 39.2 (#135), Qwen3.5 Max Preview: 41.8 (#107)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Expert | 1379 | 1489 |
| Vectara Hallucination Rate | 9.1% | — |
Multilingual Qwen3.5 Max Preview leads
MiniMax-M2.5: 47.1 (#152), Qwen3.5 Max Preview: 56.2 (#22)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Non-English | 1338 | 1465 |
| LMArena Chinese | 1393 | 1534 |
| LMArena French | 1362 | 1484 |
| LMArena German | 1362 | 1487 |
| LMArena Japanese | 1171 | 1495 |
| LMArena Korean | 1232 | 1438 |
| LMArena Russian | 1358 | 1471 |
| LMArena Spanish | 1354 | 1470 |
Instruction Following Qwen3.5 Max Preview leads
MiniMax-M2.5: 71.5 (#148), Qwen3.5 Max Preview: 77.0 (#31)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1353 | 1467 |
Long Context Qwen3.5 Max Preview leads
MiniMax-M2.5: 37.5 (#216), Qwen3.5 Max Preview: 45.2 (#45)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Longer Query | 1366 | 1476 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference Qwen3.5 Max Preview leads
MiniMax-M2.5: 53.9 (#153), Qwen3.5 Max Preview: 66.0 (#41)
| Benchmark | MiniMax-M2.5 | Qwen3.5 Max Preview |
|---|---|---|
| LMArena Text | 1359 | 1470 |
| LMArena Creative Writing | 1331 | 1464 |
| LMArena Multi-Turn | 1364 | 1478 |
| EQ-Bench Creative Writing | 1361 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Qwen3.5 Max Preview?
Qwen3.5 Max Preview is the stronger model overall, scoring 45.3 to 38.3 on the Noometry Index.
Is MiniMax-M2.5 or Qwen3.5 Max Preview better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 44.0 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and Qwen3.5 Max Preview share?
17 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Qwen3.5 Max Preview has 17.