Model comparison
MiniMax-M2.1 vs Mistral 7B
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 23.0 on the Noometry Index. Mistral 7B costs 2.1× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
MiniMax
Mistral AISummary
- They share 16 benchmarks with published results for both. MiniMax-M2.1 scores higher in 8 categories and Mistral 7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.1 leads 38.3 to 7.4.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- MiniMax-M2.1 accepts more context: 205K tokens versus 8K.
Side by side
| MiniMax-M2.1 | Mistral 7B | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 38.9 | 23.0 |
| Released | 2025-12-23 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 205K | 8K |
| Max output | 131K | 8K |
| Input $ / M tokens | $0.30 | $0.25 |
| Output $ / M tokens | $1.20 | $0.25 |
| Results tracked | 22 | 37 |
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), Mistral 7B: 26.4 (#326)
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| LMArena Coding | 1421 | 1082 |
| LMArena WebDev | 1384 | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 623.83 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Agentic & Tool Use Not comparable
MiniMax-M2.1: 27.9 (#98), Mistral 7B: —
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| Terminal-Bench | 36.6% | — |
Reasoning MiniMax-M2.1 leads
MiniMax-M2.1: 16.6 (#302), Mistral 7B: 13.1 (#336)
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| LMArena Hard Prompts | 1411 | 1067 |
| NYT Connections (extended) | 11.2% | — |
| Chess Puzzles | — | 0% |
| DTBench | — | 42.5% |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| Epoch Capabilities Index | — | 112.21 |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#138), Mistral 7B: 8.1 (#325)
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| LMArena Math | 1397 | 1085 |
| OTIS Mock AIME 2024-2025 | — | 0.3% |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge MiniMax-M2.1 leads
MiniMax-M2.1: 38.3 (#147), Mistral 7B: 7.4 (#311)
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| LMArena Expert | 1431 | 1036 |
| GPQA Diamond | — | 15.2% |
| Vectara Hallucination Rate | 11.8% | — |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multilingual MiniMax-M2.1 leads
MiniMax-M2.1: 50.0 (#128), Mistral 7B: 25.8 (#283)
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1378 | 1012 |
| LMArena Chinese | 1430 | 1009 |
| LMArena French | 1404 | 1037 |
| LMArena German | 1381 | 987 |
| LMArena Japanese | 1287 | 878 |
| LMArena Russian | 1387 | 1018 |
| LMArena Spanish | 1397 | 1026 |
| LMArena Korean | 1298 | — |
Instruction Following MiniMax-M2.1 leads
MiniMax-M2.1: 73.8 (#112), Mistral 7B: 54.2 (#280)
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1400 | 1060 |
Long Context MiniMax-M2.1 leads
MiniMax-M2.1: 43.2 (#101), Mistral 7B: 32.2 (#271)
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1416 | 1060 |
Writing & Preference MiniMax-M2.1 leads
MiniMax-M2.1: 58.3 (#120), Mistral 7B: 30.7 (#286)
| Benchmark | MiniMax-M2.1 | Mistral 7B |
|---|---|---|
| LMArena Text | 1392 | 1090 |
| LMArena Creative Writing | 1361 | 1068 |
| LMArena Multi-Turn | 1396 | 1062 |
Frequently asked questions
Is MiniMax-M2.1 better than Mistral 7B?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 23.0 on the Noometry Index. Mistral 7B costs 2.1× less per token, which makes it the better buy when MiniMax-M2.1's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.1 or Mistral 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is MiniMax-M2.1 or Mistral 7B better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.1 does, with 205K tokens against 8K.
How many benchmarks do MiniMax-M2.1 and Mistral 7B share?
16 benchmarks have published results for both models. MiniMax-M2.1 has 22 scored results on Noometry and Mistral 7B has 37.