Model comparison
MiniMax-M2.7 vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 5.6× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M2.7 scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 52.2 to 24.9.
- The biggest single-benchmark swing is NYT Connections (extended): 24.7% for MiniMax-M2.7 and 74.1% for Qwen3.6 Max Preview.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 205K.
- MiniMax-M2.7 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M2.7 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.4 | 51.1 |
| Released | 2026-03-18 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 205K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.30 | $1.30 |
| Output $ / M tokens | $1.20 | $7.80 |
| Results tracked | 30 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
MiniMax-M2.7: 41.4 (#115), Qwen3.6 Max Preview: 48.6 (#50)
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1397 | 1482 |
| LMArena Coding | 1454 | 1472 |
| SWE-bench Verified | — | 76.7% |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.7: 24.9 (#103), Qwen3.6 Max Preview: —
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
MiniMax-M2.7: 19.0 (#248), Qwen3.6 Max Preview: 40.8 (#47)
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| NYT Connections (extended) | 24.7% | 74.1% |
| LMArena Hard Prompts | 1422 | 1457 |
| Epoch Capabilities Index | 145.84 | 149.27 |
| SimpleBench | — | 63% |
| CritPt | 0.6% | — |
| Chess Puzzles | — | 20% |
| Thematic Generalization | 39.3% | — |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
Math Qwen3.6 Max Preview leads
MiniMax-M2.7: 24.9 (#254), Qwen3.6 Max Preview: 52.2 (#40)
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1420 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| ProofBench | 3% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
MiniMax-M2.7: 37.1 (#151), Qwen3.6 Max Preview: 57.6 (#35)
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1443 | 1476 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
| Vectara Hallucination Rate | 12.9% | — |
Multilingual Qwen3.6 Max Preview leads
MiniMax-M2.7: 50.5 (#120), Qwen3.6 Max Preview: 54.3 (#46)
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1382 | 1436 |
| LMArena Chinese | 1439 | 1487 |
| LMArena French | 1422 | 1449 |
| LMArena Russian | 1383 | 1444 |
| LMArena Spanish | 1403 | 1452 |
| LMArena German | 1398 | — |
| LMArena Japanese | 1261 | — |
| LMArena Korean | 1313 | — |
Instruction Following Qwen3.6 Max Preview leads
MiniMax-M2.7: 74.2 (#101), Qwen3.6 Max Preview: 75.8 (#51)
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1404 | 1437 |
Long Context Qwen3.6 Max Preview leads
MiniMax-M2.7: 43.3 (#94), Qwen3.6 Max Preview: 44.6 (#59)
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1419 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
MiniMax-M2.7: 59.1 (#107), Qwen3.6 Max Preview: 64.0 (#58)
| Benchmark | MiniMax-M2.7 | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1404 | 1447 |
| LMArena Creative Writing | 1354 | 1435 |
| LMArena Multi-Turn | 1413 | 1456 |
Frequently asked questions
Is MiniMax-M2.7 better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.1 to 37.4 on the Noometry Index. MiniMax-M2.7 costs 5.6× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.7 or Qwen3.6 Max Preview?
MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is MiniMax-M2.7 or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.6 versus 41.4 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 205K.
How many benchmarks do MiniMax-M2.7 and Qwen3.6 Max Preview share?
17 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen3.6 Max Preview has 29.