Model comparison
MiniMax-M3 vs Qwen1.5 4b Chat
MiniMax-M3 is the stronger model overall, scoring 43.8 to 28.8 on the Noometry Index.
Last verified . 13 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Qwen1.5 4b Chat in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M3 leads 62.1 to 23.8.
Side by side
| MiniMax-M3 | Qwen1.5 4b Chat | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.8 | 28.8 |
| Released | 2026-06-01 | — |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 512K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 41 | 13 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), Qwen1.5 4b Chat: 29.1 (#308)
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Coding | 1469 | 999 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Qwen1.5 4b Chat: —
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| APEX-Agents | 37.7% | — |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 30.1 (#87), Qwen1.5 4b Chat: 18.5 (#279)
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Hard Prompts | 1447 | 976 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Chess Puzzles | 14% | — |
| Mystery Game Puzzles | 8% | — |
| DTBench | 78.9% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 146.95 | — |
| ForecastBench | 61.4 | — |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), Qwen1.5 4b Chat: 30.4 (#234)
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Math | 1429 | 1026 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Qwen1.5 4b Chat: 26.7 (#255)
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Expert | 1461 | 980 |
| GPQA Diamond | 90.9% | — |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Qwen1.5 4b Chat: —
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), Qwen1.5 4b Chat: 24.1 (#290)
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Non-English | 1420 | 979 |
| LMArena Chinese | 1463 | 1024 |
| LMArena German | 1426 | 902 |
| LMArena Russian | 1428 | 952 |
| LMArena French | 1447 | — |
| LMArena Japanese | 1381 | — |
| LMArena Korean | 1372 | — |
| LMArena Spanish | 1432 | — |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Qwen1.5 4b Chat: 49.0 (#300)
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Instruction Following | 1433 | 978 |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Qwen1.5 4b Chat: 30.1 (#290)
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Longer Query | 1445 | 988 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Qwen1.5 4b Chat: 23.8 (#309)
| Benchmark | MiniMax-M3 | Qwen1.5 4b Chat |
|---|---|---|
| LMArena Text | 1433 | 997 |
| LMArena Creative Writing | 1404 | 969 |
| LMArena Multi-Turn | 1442 | 977 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Qwen1.5 4b Chat?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 28.8 on the Noometry Index.
Is MiniMax-M3 or Qwen1.5 4b Chat better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 29.1 in the Noometry coding category.
How many benchmarks do MiniMax-M3 and Qwen1.5 4b Chat share?
13 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen1.5 4b Chat has 13.