Model comparison
MiniMax-M2.7 vs Qwen3.5 397B-A17B
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 2.6× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. MiniMax-M2.7 scores higher in 0 categories and Qwen3.5 397B-A17B in 9 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.5 397B-A17B leads 46.1 to 25.9.
- The biggest single-benchmark swing is NYT Connections (extended): 24.7% for MiniMax-M2.7 and 58.9% for Qwen3.5 397B-A17B.
- MiniMax-M2.7 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.60 / $3.60 for Qwen3.5 397B-A17B.
- Qwen3.5 397B-A17B accepts more context: 262K tokens versus 205K.
Side by side
| MiniMax-M2.7 | Qwen3.5 397B-A17B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 37.7 | 46.0 |
| Released | 2026-03-18 | 2026-02-01 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $0.30 | $0.60 |
| Output $ / M tokens | $1.20 | $3.60 |
| Results tracked | 30 | 36 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
MiniMax-M2.7: 41.8 (#120), Qwen3.5 397B-A17B: 42.0 (#114)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena WebDev | 1398 | 1400 |
| LMArena Coding | 1454 | 1465 |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use Qwen3.5 397B-A17B leads
MiniMax-M2.7: 25.1 (#111), Qwen3.5 397B-A17B: 33.3 (#53)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| APEX-Agents | — | 24.9% |
| τ²-bench Airline | — | 81.5% |
| τ²-bench Banking | — | 9.8% |
| τ²-bench Retail | — | 84.4% |
| τ²-bench Telecom | — | 97.8% |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning Qwen3.5 397B-A17B leads
MiniMax-M2.7: 19.7 (#253), Qwen3.5 397B-A17B: 34.5 (#70)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| NYT Connections (extended) | 24.7% | 58.9% |
| Thematic Generalization | 39.3% | 65.1% |
| LMArena Hard Prompts | 1422 | 1448 |
| Epoch Capabilities Index | 145.85 | 146.65 |
| Kagi LLM Benchmark | — | 73.7% |
| CritPt | 0.6% | — |
| Chess Puzzles | — | 13% |
| Mystery Game Puzzles | — | 18% |
| DTBench | — | 87.5% |
| LMCA | — | 37.9% |
Math Qwen3.5 397B-A17B leads
MiniMax-M2.7: 25.9 (#263), Qwen3.5 397B-A17B: 46.1 (#73)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Math | 1420 | 1454 |
| FrontierMath (Tiers 1-3) | — | 31.2% |
| OTIS Mock AIME 2024-2025 | — | 88.9% |
| ProofBench | 3% | — |
Knowledge Qwen3.5 397B-A17B leads
MiniMax-M2.7: 37.7 (#152), Qwen3.5 397B-A17B: 53.3 (#58)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Expert | 1444 | 1462 |
| GPQA Diamond | — | 86.4% |
| Vectara Hallucination Rate | 12.9% | — |
Multimodal Not comparable
MiniMax-M2.7: —, Qwen3.5 397B-A17B: 40.7 (#44)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Vision | — | 1263 |
Multilingual Qwen3.5 397B-A17B leads
MiniMax-M2.7: 50.3 (#123), Qwen3.5 397B-A17B: 53.7 (#59)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Non-English | 1382 | 1430 |
| LMArena Chinese | 1441 | 1500 |
| LMArena French | 1421 | 1461 |
| LMArena German | 1398 | 1447 |
| LMArena Japanese | 1262 | 1426 |
| LMArena Korean | 1313 | 1384 |
| LMArena Russian | 1383 | 1429 |
| LMArena Spanish | 1403 | 1441 |
Instruction Following Too close to call
MiniMax-M2.7: 74.1 (#103), Qwen3.5 397B-A17B: 75.0 (#77)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1424 |
Long Context Too close to call
MiniMax-M2.7: 43.3 (#99), Qwen3.5 397B-A17B: 44.1 (#74)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Longer Query | 1419 | 1442 |
Writing & Preference Qwen3.5 397B-A17B leads
MiniMax-M2.7: 58.9 (#112), Qwen3.5 397B-A17B: 62.3 (#79)
| Benchmark | MiniMax-M2.7 | Qwen3.5 397B-A17B |
|---|---|---|
| LMArena Text | 1405 | 1438 |
| LMArena Creative Writing | 1354 | 1401 |
| LMArena Multi-Turn | 1412 | 1446 |
| EQ-Bench Creative Writing | — | 1478 |
Frequently asked questions
Is MiniMax-M2.7 better than Qwen3.5 397B-A17B?
Qwen3.5 397B-A17B is the stronger model overall, scoring 46.0 to 37.7 on the Noometry Index. MiniMax-M2.7 costs 2.6× less per token, which makes it the better buy when Qwen3.5 397B-A17B's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.7 or Qwen3.5 397B-A17B?
MiniMax-M2.7 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.5 397B-A17B lists at $0.60 and $3.60.
Is MiniMax-M2.7 or Qwen3.5 397B-A17B better for coding?
They score almost the same on coding (41.8 vs 42.0); test both on your own repository before choosing.
Which has the bigger context window?
Qwen3.5 397B-A17B does, with 262K tokens against 205K.
How many benchmarks do MiniMax-M2.7 and Qwen3.5 397B-A17B share?
21 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Qwen3.5 397B-A17B has 36.