Model comparison
Codestral vs MiniMax M1
MiniMax M1 is the stronger model overall, scoring 40.3 to 30.6 on the Noometry Index. Codestral costs 2.1× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Mistral AI
MiniMaxSummary
- The widest gap is in coding, where MiniMax M1 leads 39.9 to 27.3.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.55 / $2.20 for MiniMax M1.
- MiniMax M1 accepts more context: 1M tokens versus 256K.
- MiniMax M1 has downloadable open weights; the other is API-only.
Side by side
| Codestral | MiniMax M1 | |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 30.6 | 40.3 |
| Released | 2024-05-29 | 2025-06-13 |
| Weights | Proprietary | Open |
| Context window | 256K | 1M |
| Max output | 8K | 40K |
| Input $ / M tokens | $0.30 | $0.55 |
| Output $ / M tokens | $0.90 | $2.20 |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax M1 leads
Codestral: 27.3 (#321), MiniMax M1: 39.9 (#153)
| Benchmark | Codestral | MiniMax M1 |
|---|---|---|
| Aider Polyglot | 11.1% | — |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1359 |
| BigCodeBench Complete | 52.5% | — |
| ALE-Bench | 137.78 | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Reasoning MiniMax M1 leads
Codestral: 19.8 (#251), MiniMax M1: 26.9 (#126)
| Benchmark | Codestral | MiniMax M1 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| LMArena Hard Prompts | — | 1339 |
Math Not comparable
Codestral: —, MiniMax M1: 37.5 (#151)
| Benchmark | Codestral | MiniMax M1 |
|---|---|---|
| LMArena Math | — | 1361 |
Knowledge Not comparable
Codestral: —, MiniMax M1: 36.4 (#170)
| Benchmark | Codestral | MiniMax M1 |
|---|---|---|
| LMArena Expert | — | 1317 |
Multilingual Not comparable
Codestral: —, MiniMax M1: 45.8 (#163)
| Benchmark | Codestral | MiniMax M1 |
|---|---|---|
| LMArena Non-English | — | 1319 |
| LMArena Chinese | — | 1360 |
| LMArena French | — | 1370 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1217 |
| LMArena Korean | — | 1266 |
| LMArena Russian | — | 1329 |
| LMArena Spanish | — | 1353 |
Instruction Following Not comparable
Codestral: —, MiniMax M1: 69.3 (#174)
| Benchmark | Codestral | MiniMax M1 |
|---|---|---|
| LMArena Instruction Following | — | 1312 |
Long Context Not comparable
Codestral: —, MiniMax M1: 41.4 (#141)
| Benchmark | Codestral | MiniMax M1 |
|---|---|---|
| Fiction.LiveBench | — | 69.4% |
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Codestral: —, MiniMax M1: 53.1 (#161)
| Benchmark | Codestral | MiniMax M1 |
|---|---|---|
| LMArena Text | — | 1343 |
| LMArena Creative Writing | — | 1298 |
| LMArena Multi-Turn | — | 1335 |
Frequently asked questions
Is Codestral better than MiniMax M1?
MiniMax M1 is the stronger model overall, scoring 40.3 to 30.6 on the Noometry Index. Codestral costs 2.1× less per token, which makes it the better buy when MiniMax M1's lead doesn't matter for your workload.
Which is cheaper, Codestral or MiniMax M1?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; MiniMax M1 lists at $0.55 and $2.20.
Is Codestral or MiniMax M1 better for coding?
MiniMax M1 scores higher on coding benchmarks: 39.9 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
MiniMax M1 does, with 1M tokens against 256K.
How many benchmarks do Codestral and MiniMax M1 share?
0 benchmarks have published results for both models. Codestral has 7 scored results on Noometry and MiniMax M1 has 18.