Model comparison
MiniMax-M3 vs Qwen-14B
MiniMax-M3 is the stronger model overall, scoring 43.8 to 31.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. MiniMax-M3 scores higher in 7 categories and Qwen-14B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M3 leads 62.1 to 27.6.
Side by side
| MiniMax-M3 | Qwen-14B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 43.8 | 31.4 |
| Released | 2026-06-01 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 1M | — |
| Max output | 512K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 41 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), Qwen-14B: 31.2 (#288)
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1469 | 1071 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| ALE-Bench | 640.02 | — |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Qwen-14B: —
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| 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), Qwen-14B: 19.6 (#257)
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1447 | 1027 |
| Epoch Capabilities Index | 146.95 | 113.03 |
| 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% | — |
| BIG-Bench Hard | — | 55% |
| ForecastBench | 61.4 | — |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), Qwen-14B: 31.2 (#227)
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| LMArena Math | 1429 | 1068 |
| OTIS Mock AIME 2024-2025 | 71.1% | — |
| ProofBench | 18% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
MiniMax-M3: 58.4 (#35), Qwen-14B: —
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| GPQA Diamond | 90.9% | — |
| LMArena Expert | 1461 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Qwen-14B: —
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), Qwen-14B: 27.5 (#275)
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1420 | 1041 |
| LMArena Chinese | 1463 | 1077 |
| LMArena French | 1447 | — |
| LMArena German | 1426 | — |
| LMArena Japanese | 1381 | — |
| LMArena Korean | 1372 | — |
| LMArena Russian | 1428 | — |
| LMArena Spanish | 1432 | — |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Qwen-14B: 52.4 (#289)
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1031 |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Qwen-14B: 31.3 (#280)
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1445 | 1028 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Qwen-14B: 27.6 (#299)
| Benchmark | MiniMax-M3 | Qwen-14B |
|---|---|---|
| LMArena Text | 1433 | 1051 |
| LMArena Creative Writing | 1404 | 1028 |
| LMArena Multi-Turn | 1442 | 1022 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Qwen-14B?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 31.4 on the Noometry Index.
Is MiniMax-M3 or Qwen-14B better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 31.2 in the Noometry coding category.
How many benchmarks do MiniMax-M3 and Qwen-14B share?
11 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Qwen-14B has 18.