Model comparison
Devstral Small 2505 vs MiniMax-M2.7
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.5× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.
Last verified . 2 shared benchmarks.
Mistral AI
MiniMaxSummary
- They share 2 benchmarks with published results for both. Devstral Small 2505 scores higher in 1 category and MiniMax-M2.7 in 1 category; one gap is clear of the uncertainty.
- The biggest single-benchmark swing is SciCode: 28.8% for Devstral Small 2505 and 47% for MiniMax-M2.7.
- Devstral Small 2505 is cheaper at $0.10 / $0.30 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- MiniMax-M2.7 accepts more context: 205K tokens versus 128K.
Side by side
| Devstral Small 2505 | MiniMax-M2.7 | |
|---|---|---|
| Provider | Mistral AI | MiniMax |
| Noometry Index | 34.3 | 37.7 |
| Released | 2025-05-07 | 2026-03-18 |
| Weights | Open | Open |
| Context window | 128K | 205K |
| Max output | 128K | 131K |
| Input $ / M tokens | $0.10 | $0.30 |
| Output $ / M tokens | $0.30 | $1.20 |
| Results tracked | 4 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
Devstral Small 2505: 38.9 (#166), MiniMax-M2.7: 41.8 (#120)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| SciCode | 28.8% | 47% |
| SWE-bench Verified (bash only) | 56.4% | — |
| LMArena WebDev | — | 1398 |
| WeirdML | — | 37% |
| LMArena Coding | — | 1454 |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use Not comparable
Devstral Small 2505: —, MiniMax-M2.7: 25.1 (#111)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning Too close to call
Devstral Small 2505: 19.7 (#252), MiniMax-M2.7: 19.7 (#253)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| CritPt | 0% | 0.6% |
| Kagi LLM Benchmark | 37.7% | — |
| NYT Connections (extended) | — | 24.7% |
| Thematic Generalization | — | 39.3% |
| LMArena Hard Prompts | — | 1422 |
| Epoch Capabilities Index | — | 145.85 |
Math Not comparable
Devstral Small 2505: —, MiniMax-M2.7: 25.9 (#263)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| ProofBench | — | 3% |
| LMArena Math | — | 1420 |
Knowledge Not comparable
Devstral Small 2505: —, MiniMax-M2.7: 37.7 (#152)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| Vectara Hallucination Rate | — | 12.9% |
| LMArena Expert | — | 1444 |
Multilingual Not comparable
Devstral Small 2505: —, MiniMax-M2.7: 50.3 (#123)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | — | 1382 |
| LMArena Chinese | — | 1441 |
| LMArena French | — | 1421 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1313 |
| LMArena Russian | — | 1383 |
| LMArena Spanish | — | 1403 |
Instruction Following Not comparable
Devstral Small 2505: —, MiniMax-M2.7: 74.1 (#103)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | — | 1405 |
Long Context Not comparable
Devstral Small 2505: —, MiniMax-M2.7: 43.3 (#99)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | — | 1419 |
Writing & Preference Not comparable
Devstral Small 2505: —, MiniMax-M2.7: 58.9 (#112)
| Benchmark | Devstral Small 2505 | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | — | 1405 |
| LMArena Creative Writing | — | 1354 |
| LMArena Multi-Turn | — | 1412 |
Frequently asked questions
Is Devstral Small 2505 better than MiniMax-M2.7?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 34.3 on the Noometry Index. Devstral Small 2505 costs 3.5× less per token, which makes it the better buy when MiniMax-M2.7's lead doesn't matter for your workload.
Which is cheaper, Devstral Small 2505 or MiniMax-M2.7?
Devstral Small 2505 is cheaper. It lists at $0.10 per million input tokens and $0.30 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.
Is Devstral Small 2505 or MiniMax-M2.7 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.7 does, with 205K tokens against 128K.
How many benchmarks do Devstral Small 2505 and MiniMax-M2.7 share?
2 benchmarks have published results for both models. Devstral Small 2505 has 4 scored results on Noometry and MiniMax-M2.7 has 30.