Model comparison
MiniMax-M3 vs Qwen3.5 Plus
MiniMax-M3 is the stronger model overall, scoring 43.5 to 42.3 on the Noometry Index.
Last verified . 9 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. MiniMax-M3 scores higher in 2 categories and Qwen3.5 Plus in 2 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 46.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for MiniMax-M3 and 86.7% for Qwen3.5 Plus.
- MiniMax-M3 is cheaper at $0.30 / $1.20 per million input/output tokens, against $0.40 / $2.40 for Qwen3.5 Plus.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| MiniMax-M3 | Qwen3.5 Plus | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.5 | 42.3 |
| Released | 2026-06-01 | 2026-02-16 |
| Weights | Open | Proprietary |
| Context window | 1M | 1M |
| Max output | 512K | 66K |
| Input $ / M tokens | $0.30 | $0.40 |
| Output $ / M tokens | $1.20 | $2.40 |
| Results tracked | 41 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
MiniMax-M3: 41.5 (#111), Qwen3.5 Plus: —
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| ALE-Bench | 640.02 | 621.92 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| LMArena Coding | 1470 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.5 (#121), Qwen3.5 Plus: —
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| Vending-Bench 2 | 2,158 | 0.54 |
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
Reasoning Qwen3.5 Plus leads
MiniMax-M3: 29.3 (#83), Qwen3.5 Plus: 32.0 (#67)
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| Chess Puzzles | 14% | 22% |
| Mystery Game Puzzles | 8% | 17% |
| DTBench | 78.9% | 80.5% |
| LMCA | 33.7% | 36.4% |
| Epoch Capabilities Index | 147 | 146.79 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| LMArena Hard Prompts | 1447 | — |
| Surface Evolver Bench | 55% | — |
| ForecastBench | 61.4 | — |
Math Qwen3.5 Plus leads
MiniMax-M3: 39.1 (#83), Qwen3.5 Plus: 47.9 (#55)
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 86.7% |
| ProofBench | 18% | — |
| LMArena Math | 1432 | — |
| FrontierMath (Feb 2025 set) | — | 21% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#32), Qwen3.5 Plus: 46.0 (#78)
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| GPQA Diamond | 90.9% | 84.8% |
| SimpleQA Verified | — | 25.4% |
| Vectara Hallucination Rate | — | 10.7% |
| LMArena Expert | 1462 | — |
Multimodal Not comparable
MiniMax-M3: 39.5 (#45), Qwen3.5 Plus: —
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| LMArena Vision | 1254 | — |
| LMArena Document | 1435 | — |
Multilingual Not comparable
MiniMax-M3: 53.2 (#70), Qwen3.5 Plus: —
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| LMArena Non-English | 1420 | — |
| LMArena Chinese | 1465 | — |
| LMArena French | 1445 | — |
| LMArena German | 1424 | — |
| LMArena Japanese | 1381 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1430 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Not comparable
MiniMax-M3: 75.7 (#56), Qwen3.5 Plus: —
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#68), Qwen3.5 Plus: 42.9 (#109)
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| CL-bench | — | 19.8% |
| CL-bench Life | — | 12.4% |
| LMArena Longer Query | 1445 | — |
Writing & Preference Not comparable
MiniMax-M3: 62.3 (#79), Qwen3.5 Plus: —
| Benchmark | MiniMax-M3 | Qwen3.5 Plus |
|---|---|---|
| LMArena Text | 1433 | — |
| LMArena Creative Writing | 1405 | — |
| EQ-Bench 4 | 1150 | — |
| LMArena Multi-Turn | 1441 | — |
Frequently asked questions
Is MiniMax-M3 better than Qwen3.5 Plus?
MiniMax-M3 is the stronger model overall, scoring 43.5 to 42.3 on the Noometry Index.
Which is cheaper, MiniMax-M3 or Qwen3.5 Plus?
MiniMax-M3 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen3.5 Plus lists at $0.40 and $2.40.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do MiniMax-M3 and Qwen3.5 Plus share?
9 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen3.5 Plus has 15.