Model comparison
Codestral vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.6 on the Noometry Index.
Last verified . 1 shared benchmarks.
Mistral AI
MiniMaxSummary
- They share 1 benchmark with published results for both. Codestral scores higher in 0 categories and MiniMax-M3 in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M3 leads 41.8 to 27.3.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 256K.
- MiniMax-M3 has downloadable open weights; the other is API-only.
Side by side
| Codestral | MiniMax-M3 | |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 30.6 | 43.8 |
| Released | 2024-05-29 | 2026-06-01 |
| Weights | Proprietary | Open |
| Context window | 256K | 1M |
| Max output | 8K | 512K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $0.90 | $1.20 |
| Results tracked | 7 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M3 leads
Codestral: 27.3 (#321), MiniMax-M3: 41.8 (#118)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| ALE-Bench | 137.78 | 640.02 |
| FrontierCode | — | 14.7% |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1469 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, MiniMax-M3: 22.6 (#130)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Codestral: 19.8 (#251), MiniMax-M3: 30.1 (#87)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| SimpleBench | — | 45.8% |
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| Chess Puzzles | — | 14% |
| LMArena Hard Prompts | — | 1447 |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 146.95 |
| ForecastBench | — | 61.4 |
Math Not comparable
Codestral: —, MiniMax-M3: 40.0 (#95)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 71.1% |
| ProofBench | — | 18% |
| LMArena Math | — | 1429 |
Knowledge Not comparable
Codestral: —, MiniMax-M3: 58.4 (#35)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | — | 90.9% |
| LMArena Expert | — | 1461 |
Multimodal Not comparable
Codestral: —, MiniMax-M3: 40.2 (#51)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
Multilingual Not comparable
Codestral: —, MiniMax-M3: 53.0 (#75)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | — | 1420 |
| LMArena Chinese | — | 1463 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1432 |
Instruction Following Not comparable
Codestral: —, MiniMax-M3: 75.5 (#62)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| LMArena Instruction Following | — | 1433 |
Long Context Not comparable
Codestral: —, MiniMax-M3: 44.2 (#72)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | — | 1445 |
Writing & Preference Not comparable
Codestral: —, MiniMax-M3: 62.1 (#83)
| Benchmark | Codestral | MiniMax-M3 |
|---|---|---|
| LMArena Text | — | 1433 |
| LMArena Creative Writing | — | 1404 |
| EQ-Bench 4 | — | 1150 |
| LMArena Multi-Turn | — | 1442 |
Frequently asked questions
Is Codestral better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or MiniMax-M3?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Is Codestral or MiniMax-M3 better for coding?
MiniMax-M3 scores higher on coding benchmarks: 41.8 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 256K.
How many benchmarks do Codestral and MiniMax-M3 share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and MiniMax-M3 has 41.