Model comparison
Codestral vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 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 1 category and MiniMax-M2.1 in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.1 leads 40.4 to 27.3.
- Codestral is cheaper at $0.30 / $0.90 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.1.
- Codestral accepts more context: 256K tokens versus 205K.
- MiniMax-M2.1 has downloadable open weights; the other is API-only.
Side by side
| Codestral | MiniMax-M2.1 | |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 30.6 | 38.9 |
| Released | 2024-05-29 | 2025-12-23 |
| Weights | Proprietary | Open |
| Context window | 256K | 205K |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.30 | $0.30 |
| Output $ / M tokens | $0.90 | $1.20 |
| Results tracked | 7 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Codestral: 27.3 (#321), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| ALE-Bench | 137.78 | 623.83 |
| Aider Polyglot | 11.1% | — |
| LMArena WebDev | — | 1384 |
| BigCodeBench Instruct | 41.8% | — |
| LMArena Coding | — | 1421 |
| BigCodeBench Complete | 52.5% | — |
| HumanEval+ | 73.8% | — |
| MBPP+ | 61.9% | — |
Agentic & Tool Use Not comparable
Codestral: —, MiniMax-M2.1: 27.9 (#98)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
Reasoning Codestral leads
Codestral: 19.8 (#251), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| Kagi LLM Benchmark | 32.5% | — |
| NYT Connections (extended) | — | 11.2% |
| LMArena Hard Prompts | — | 1411 |
Math Not comparable
Codestral: —, MiniMax-M2.1: 38.3 (#138)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | — | 1397 |
Knowledge Not comparable
Codestral: —, MiniMax-M2.1: 38.3 (#147)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| Vectara Hallucination Rate | — | 11.8% |
| LMArena Expert | — | 1431 |
Multilingual Not comparable
Codestral: —, MiniMax-M2.1: 50.0 (#128)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | — | 1378 |
| LMArena Chinese | — | 1430 |
| LMArena French | — | 1404 |
| LMArena German | — | 1381 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1298 |
| LMArena Russian | — | 1387 |
| LMArena Spanish | — | 1397 |
Instruction Following Not comparable
Codestral: —, MiniMax-M2.1: 73.8 (#112)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | — | 1400 |
Long Context Not comparable
Codestral: —, MiniMax-M2.1: 43.2 (#101)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | — | 1416 |
Writing & Preference Not comparable
Codestral: —, MiniMax-M2.1: 58.3 (#120)
| Benchmark | Codestral | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | — | 1392 |
| LMArena Creative Writing | — | 1361 |
| LMArena Multi-Turn | — | 1396 |
Frequently asked questions
Is Codestral better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 30.6 on the Noometry Index.
Which is cheaper, Codestral or MiniMax-M2.1?
Codestral is cheaper. It lists at $0.30 per million input tokens and $0.90 per million output tokens; MiniMax-M2.1 lists at $0.30 and $1.20.
Is Codestral or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 27.3 in the Noometry coding category.
Which has the bigger context window?
Codestral does, with 256K tokens against 205K.
How many benchmarks do Codestral and MiniMax-M2.1 share?
1 benchmark has published results for both models. Codestral has 7 scored results on Noometry and MiniMax-M2.1 has 22.