Model comparison
MiniMax-M2.1 vs Qwen2.5 72B Instruct
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.9 on the Noometry Index.
Last verified . 17 shared benchmarks.
MiniMax
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. MiniMax-M2.1 scores higher in 8 categories and Qwen2.5 72B Instruct in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2.1 leads 38.3 to 19.3.
- MiniMax-M2.1 is cheaper at $0.30 / $1.20 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- MiniMax-M2.1 accepts more context: 205K tokens versus 131K.
Side by side
| MiniMax-M2.1 | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | MiniMax | Alibaba (Qwen) |
| Noometry Index | 38.9 | 31.9 |
| Released | 2025-12-23 | 2024-09 |
| Weights | Open | Open |
| Context window | 205K | 131K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.30 | $1.40 |
| Output $ / M tokens | $1.20 | $5.60 |
| Results tracked | 22 | 43 |
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), Qwen2.5 72B Instruct: 33.2 (#260)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1421 | 1292 |
| LMArena WebDev | 1384 | — |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 623.83 | — |
Agentic & Tool Use MiniMax-M2.1 leads
MiniMax-M2.1: 27.9 (#98), Qwen2.5 72B Instruct: 22.1 (#133)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| Terminal-Bench | 36.6% | — |
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning Qwen2.5 72B Instruct leads
MiniMax-M2.1: 16.6 (#302), Qwen2.5 72B Instruct: 22.3 (#199)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1271 |
| NYT Connections (extended) | 11.2% | — |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Qwen2.5 72B Instruct: 19.3 (#287)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1397 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), Qwen2.5 72B Instruct: 27.0 (#253)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1431 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 11.8% | — |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), Qwen2.5 72B Instruct: 41.0 (#213)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1378 | 1252 |
| LMArena Chinese | 1430 | 1272 |
| LMArena French | 1404 | 1280 |
| LMArena German | 1381 | 1234 |
| LMArena Japanese | 1287 | 1180 |
| LMArena Korean | 1298 | 1188 |
| LMArena Russian | 1387 | 1264 |
| LMArena Spanish | 1397 | 1256 |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), Qwen2.5 72B Instruct: 65.5 (#221)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1400 | 1254 |
| IFEval | — | 80.6% |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), Qwen2.5 72B Instruct: 38.9 (#188)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1416 | 1282 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), Qwen2.5 72B Instruct: 46.7 (#215)
| Benchmark | MiniMax-M2.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1392 | 1269 |
| LMArena Creative Writing | 1361 | 1221 |
| LMArena Multi-Turn | 1396 | 1272 |
| WildBench | — | 80.2% |
Frequently asked questions
Is MiniMax-M2.1 better than Qwen2.5 72B Instruct?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 31.9 on the Noometry Index.
Which is cheaper, MiniMax-M2.1 or Qwen2.5 72B Instruct?
MiniMax-M2.1 is cheaper. It lists at $0.30 per million input tokens and $1.20 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.
Is MiniMax-M2.1 or Qwen2.5 72B Instruct better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 33.2 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 131K.
How many benchmarks do MiniMax-M2.1 and Qwen2.5 72B Instruct share?
17 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Qwen2.5 72B Instruct has 43.