Model comparison
MiniMax-M3 vs Mistral 7B
MiniMax-M3 is the stronger model overall, scoring 43.8 to 23.0 on the Noometry Index. Mistral 7B costs 2.1× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
MiniMax
Mistral AISummary
- They share 21 benchmarks with published results for both. MiniMax-M3 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-M3 leads 58.4 to 7.4.
- The biggest single-benchmark swing is GPQA Diamond: 90.9% for MiniMax-M3 and 15.2% for Mistral 7B.
- Mistral 7B is cheaper at $0.25 / $0.25 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 8K.
Side by side
| MiniMax-M3 | Mistral 7B | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 43.8 | 23.0 |
| Released | 2026-06-01 | 2023-09-27 |
| Weights | Open | Open |
| Context window | 1M | 8K |
| Max output | 512K | 8K |
| Input $ / M tokens | $0.30 | $0.25 |
| Output $ / M tokens | $1.20 | $0.25 |
| Results tracked | 41 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
MiniMax-M3: 41.8 (#118), Mistral 7B: 26.4 (#326)
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| LMArena Coding | 1469 | 1082 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| SciCode | 47.1% | — |
| BigCodeBench Instruct | — | 19.5% |
| BigCodeBench Complete | — | 27.3% |
| ALE-Bench | 640.02 | — |
| HumanEval+ | — | 36% |
| MBPP+ | — | 42.1% |
Agentic & Tool Use Not comparable
MiniMax-M3: 22.6 (#130), Mistral 7B: —
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| 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), Mistral 7B: 13.1 (#336)
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| Chess Puzzles | 14% | 0% |
| LMArena Hard Prompts | 1447 | 1067 |
| DTBench | 78.9% | 42.5% |
| Epoch Capabilities Index | 146.95 | 112.21 |
| SimpleBench | 45.8% | — |
| NYT Connections (extended) | 65.1% | — |
| CritPt | 3.7% | — |
| Mystery Game Puzzles | 8% | — |
| LMCA | 33.7% | — |
| Surface Evolver Bench | 55% | — |
| Adversarial NLI | — | 47.1% |
| BIG-Bench Hard | — | 56.1% |
| ForecastBench | 61.4 | — |
| HellaSwag | — | 81% |
| PIQA | — | 83% |
| WinoGrande | — | 75.3% |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), Mistral 7B: 8.1 (#325)
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 0.3% |
| LMArena Math | 1429 | 1085 |
| ProofBench | 18% | — |
| MATH Level 5 | — | 3.7% |
| GSM8K | — | 54.4% |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Mistral 7B: 7.4 (#311)
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| GPQA Diamond | 90.9% | 15.2% |
| LMArena Expert | 1461 | 1036 |
| ARC (AI2) Challenge | — | 78.6% |
| BoolQ | — | 87.4% |
| MMLU | — | 62.5% |
| OpenBookQA | — | 79.8% |
| TriviaQA | — | 75.2% |
Multimodal Not comparable
MiniMax-M3: 40.2 (#51), Mistral 7B: —
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| LMArena Vision | 1253 | — |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), Mistral 7B: 25.8 (#283)
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| LMArena Non-English | 1420 | 1012 |
| LMArena Chinese | 1463 | 1009 |
| LMArena French | 1447 | 1037 |
| LMArena German | 1426 | 987 |
| LMArena Japanese | 1381 | 878 |
| LMArena Russian | 1428 | 1018 |
| LMArena Spanish | 1432 | 1026 |
| LMArena Korean | 1372 | — |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Mistral 7B: 54.2 (#280)
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| LMArena Instruction Following | 1433 | 1060 |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Mistral 7B: 32.2 (#271)
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| LMArena Longer Query | 1445 | 1060 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Mistral 7B: 30.7 (#286)
| Benchmark | MiniMax-M3 | Mistral 7B |
|---|---|---|
| LMArena Text | 1433 | 1090 |
| LMArena Creative Writing | 1404 | 1068 |
| LMArena Multi-Turn | 1442 | 1062 |
| EQ-Bench 4 | 1150 | — |
Frequently asked questions
Is MiniMax-M3 better than Mistral 7B?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 23.0 on the Noometry Index. Mistral 7B costs 2.1× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M3 or Mistral 7B?
Mistral 7B is cheaper. It lists at $0.25 per million input tokens and $0.25 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is MiniMax-M3 or Mistral 7B better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 26.4 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 8K.
How many benchmarks do MiniMax-M3 and Mistral 7B share?
21 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Mistral 7B has 37.