Model comparison
MiniMax-M3 vs Mistral Small
MiniMax-M3 is the stronger model overall, scoring 43.8 to 33.4 on the Noometry Index. Mistral Small costs 2.0× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
MiniMax
Mistral AISummary
- They share 25 benchmarks with published results for both. MiniMax-M3 scores higher in 9 categories and Mistral Small in 1 category; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 31.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 71.1% for MiniMax-M3 and 5.8% for Mistral Small.
- Mistral Small is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 262K.
Side by side
| MiniMax-M3 | Mistral Small | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 43.8 | 33.4 |
| Released | 2026-06-01 | 2024-02-26 |
| Weights | Open | Open |
| Context window | 1M | 262K |
| Max output | 512K | 256K |
| Input $ / M tokens | $0.30 | $0.15 |
| Output $ / M tokens | $1.20 | $0.60 |
| Results tracked | 41 | 39 |
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 Small: 34.0 (#247)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| SciCode | 47.1% | 26.5% |
| LMArena Coding | 1469 | 1362 |
| ALE-Bench | 640.02 | 497.62 |
| FrontierCode | 14.7% | — |
| LMArena WebDev | 1482 | — |
| BigCodeBench Instruct | — | 36.1% |
| LiveBench Coding | — | 36.2% |
| BigCodeBench Complete | — | 46.6% |
Agentic & Tool Use Mistral Small leads
MiniMax-M3: 22.6 (#130), Mistral Small: 28.1 (#93)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| APEX-Agents | 37.7% | — |
| Berkeley Function Calling Leaderboard | — | 37.1% |
| OSWorld 2.0 | 4.6% | — |
| GBAEval | 0.9% | — |
| Vending-Bench 2 | 2,158 | — |
Reasoning MiniMax-M3 leads
MiniMax-M3: 30.1 (#87), Mistral Small: 19.8 (#250)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| CritPt | 3.7% | 0% |
| LMArena Hard Prompts | 1447 | 1335 |
| DTBench | 78.9% | 70.9% |
| LMCA | 33.7% | 20.6% |
| SimpleBench | 45.8% | — |
| Kagi LLM Benchmark | — | 37.8% |
| NYT Connections (extended) | 65.1% | — |
| Chess Puzzles | 14% | — |
| LiveBench Reasoning | — | 44.8% |
| Mystery Game Puzzles | 8% | — |
| LiveBench Data Analysis | — | 53.7% |
| Surface Evolver Bench | 55% | — |
| Epoch Capabilities Index | 146.95 | — |
| ForecastBench | 61.4 | — |
| LiveBench | — | 44% |
Math MiniMax-M3 leads
MiniMax-M3: 40.0 (#95), Mistral Small: 16.4 (#293)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 71.1% | 5.8% |
| LMArena Math | 1429 | 1341 |
| ProofBench | 18% | — |
| LiveBench Math | — | 39.9% |
| MATH Level 5 | — | 46.8% |
Knowledge MiniMax-M3 leads
MiniMax-M3: 58.4 (#35), Mistral Small: 31.0 (#222)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| GPQA Diamond | 90.9% | 47.5% |
| LMArena Expert | 1461 | 1291 |
| Vectara Hallucination Rate | — | 5.1% |
| MMLU | — | 68.7% |
Multimodal MiniMax-M3 leads
MiniMax-M3: 40.2 (#51), Mistral Small: 33.5 (#96)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| LMArena Vision | 1253 | 1142 |
| LMArena Document | 1435 | — |
Multilingual MiniMax-M3 leads
MiniMax-M3: 53.0 (#75), Mistral Small: 45.5 (#169)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| LMArena Non-English | 1420 | 1315 |
| LMArena Chinese | 1463 | 1340 |
| LMArena French | 1447 | 1337 |
| LMArena German | 1426 | 1340 |
| LMArena Japanese | 1381 | 1275 |
| LMArena Korean | 1372 | 1259 |
| LMArena Russian | 1428 | 1324 |
| LMArena Spanish | 1432 | 1346 |
Instruction Following MiniMax-M3 leads
MiniMax-M3: 75.5 (#62), Mistral Small: 66.4 (#209)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| LMArena Instruction Following | 1433 | 1310 |
| LiveBench Instruction Following | — | 63.7% |
Long Context MiniMax-M3 leads
MiniMax-M3: 44.2 (#72), Mistral Small: 40.4 (#156)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| LMArena Longer Query | 1445 | 1327 |
Writing & Preference MiniMax-M3 leads
MiniMax-M3: 62.1 (#83), Mistral Small: 52.5 (#171)
| Benchmark | MiniMax-M3 | Mistral Small |
|---|---|---|
| LMArena Text | 1433 | 1338 |
| LMArena Creative Writing | 1404 | 1305 |
| LMArena Multi-Turn | 1442 | 1344 |
| EQ-Bench 4 | 1150 | — |
| LiveBench Language | — | 30.5% |
Frequently asked questions
Is MiniMax-M3 better than Mistral Small?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 33.4 on the Noometry Index. Mistral Small costs 2.0× 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 Small?
Mistral Small is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is MiniMax-M3 or Mistral Small better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 34.0 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 262K.
How many benchmarks do MiniMax-M3 and Mistral Small share?
25 benchmarks have published results for both models. MiniMax-M3 has 41 scored results on Noometry and Mistral Small has 39.