Model comparison
MiniMax-M3 vs Qwen1.5-110B
MiniMax-M3 is the stronger model overall, scoring 43.8 to 34.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. MiniMax-M3 scores higher in 8 categories and Qwen1.5-110B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 31.2.
Side by side
| MiniMax-M3 | Qwen1.5-110B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.8 | 34.2 |
| Released | 2026-06-01 | 2024-04-25 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 512K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 41 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), Qwen1.5-110B: 33.0 (#264)
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Coding | 1469 | 1184 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| BigCodeBench Instruct | — | 35% |
| BigCodeBench Complete | — | 44.4% |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Qwen1.5-110B: —
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| 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), Qwen1.5-110B: 22.7 (#189)
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1168 |
| ForecastBench | 61.4 | 57.7 |
| 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 | — |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), Qwen1.5-110B: 33.7 (#201)
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Math | 1429 | 1185 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Qwen1.5-110B: 31.2 (#219)
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Expert | 1461 | 1144 |
| GPQA Diamond | 90.9% | — |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Qwen1.5-110B: —
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), Qwen1.5-110B: 33.6 (#250)
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Non-English | 1420 | 1142 |
| LMArena Chinese | 1463 | 1206 |
| LMArena French | 1447 | 1151 |
| LMArena German | 1426 | 1123 |
| LMArena Japanese | 1381 | 1074 |
| LMArena Korean | 1372 | 1044 |
| LMArena Russian | 1428 | 1118 |
| LMArena Spanish | 1432 | 1142 |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Qwen1.5-110B: 60.3 (#252)
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1158 |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Qwen1.5-110B: 35.1 (#242)
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Longer Query | 1445 | 1157 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Qwen1.5-110B: 38.0 (#255)
| Benchmark | MiniMax-M3 | Qwen1.5-110B |
|---|---|---|
| LMArena Text | 1433 | 1175 |
| LMArena Creative Writing | 1404 | 1148 |
| LMArena Multi-Turn | 1442 | 1160 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Qwen1.5-110B?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 34.2 on the Noometry Index.
Is MiniMax-M3 or Qwen1.5-110B better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 33.0 in the Noometry coding category.
How many benchmarks do MiniMax-M3 and Qwen1.5-110B share?
18 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen1.5-110B has 20.