Model comparison
MiniMax-M2.1 vs Qwen-14B
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. MiniMax-M2.1 scores higher in 6 categories and Qwen-14B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 27.6.
Side by side
| MiniMax-M2.1 | Qwen-14B | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.9 | 31.4 |
| Released | 2025-12-23 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 22 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
MiniMax-M2.1: 40.4 (#143), Qwen-14B: 31.2 (#288)
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| LMArena Coding | 1421 | 1071 |
| LMArena WebDev | 1384 | — |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.9 (#98), Qwen-14B: —
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning Qwen-14B leads
MiniMax-M2.1: 16.6 (#302), Qwen-14B: 19.6 (#257)
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1027 |
| NYT Connections (extended) | 11.2% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Qwen-14B: 31.2 (#227)
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| LMArena Math | 1397 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
MiniMax-M2.1: 38.3 (#147), Qwen-14B: —
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| Vectara Hallucination Rate | 11.8% | — |
| LMArena Expert | 1431 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), Qwen-14B: 27.5 (#275)
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1378 | 1041 |
| LMArena Chinese | 1430 | 1077 |
| LMArena French | 1404 | — |
| LMArena German | 1381 | — |
| LMArena Japanese | 1287 | — |
| LMArena Korean | 1298 | — |
| LMArena Russian | 1387 | — |
| LMArena Spanish | 1397 | — |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), Qwen-14B: 52.4 (#289)
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1031 |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), Qwen-14B: 31.3 (#280)
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1416 | 1028 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), Qwen-14B: 27.6 (#299)
| Benchmark | MiniMax-M2.1 | Qwen-14B |
|---|---|---|
| LMArena Text | 1392 | 1051 |
| LMArena Creative Writing | 1361 | 1028 |
| LMArena Multi-Turn | 1396 | 1022 |
Frequently asked questions
Is MiniMax-M2.1 better than Qwen-14B?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.4 on the Noometry Index.
Is MiniMax-M2.1 or Qwen-14B better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 31.2 in the Noometry coding category.
How many benchmarks do MiniMax-M2.1 and Qwen-14B share?
10 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Qwen-14B has 18.