Model comparison
MiniMax-M2.7 vs Ministral 8B
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 28.2 on the Noometry Index. Ministral 8B 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 . 13 shared benchmarks.
MiniMax
Mistral AISummary
- They share 13 benchmarks with published results for both. MiniMax-M2.7 scores higher in 9 categories and Ministral 8B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.7 leads 37.7 to 12.6.
- The biggest single-benchmark swing is Vectara Hallucination Rate: 12.9% for MiniMax-M2.7 and 7.4% for Ministral 8B.
- Ministral 8B is cheaper at $0.15 / $0.15 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.7.
- Ministral 8B accepts more context: 262K tokens versus 205K.
Side by side
| MiniMax-M2.7 | Ministral 8B | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 37.7 | 28.2 |
| Released | 2026-03-18 | 2024-10-01 |
| Weights | Open | Open |
| Context window | 205K | 262K |
| Max output | 131K | 262K |
| Input $ / M tokens | $0.30 | $0.15 |
| Output $ / M tokens | $1.20 | $0.15 |
| Results tracked | 30 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
MiniMax-M2.7: 41.8 (#120), Ministral 8B: 35.0 (#230)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| LMArena Coding | 1454 | 1202 |
| LMArena WebDev | 1398 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use MiniMax-M2.7 leads
MiniMax-M2.7: 25.1 (#111), Ministral 8B: 16.4 (#148)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| Berkeley Function Calling Leaderboard | — | 11.1% |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning MiniMax-M2.7 leads
MiniMax-M2.7: 19.7 (#253), Ministral 8B: 18.4 (#281)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1191 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Thematic Generalization | 39.3% | — |
| DTBench | — | 45.7% |
| Epoch Capabilities Index | 145.85 | — |
Math Too close to call
MiniMax-M2.7: 25.9 (#263), Ministral 8B: 25.7 (#267)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| LMArena Math | 1420 | 1188 |
| ProofBench | 3% | — |
| MATH Level 5 | — | 14.9% |
Knowledge MiniMax-M2.7 leads
MiniMax-M2.7: 37.7 (#152), Ministral 8B: 12.6 (#297)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| Vectara Hallucination Rate | 12.9% | 7.4% |
| LMArena Expert | 1444 | 1170 |
| GPQA Diamond | — | 27.1% |
Multilingual MiniMax-M2.7 leads
MiniMax-M2.7: 50.3 (#123), Ministral 8B: 35.1 (#247)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1382 | 1165 |
| LMArena Chinese | 1441 | 1193 |
| LMArena Russian | 1383 | 1195 |
| LMArena French | 1421 | — |
| LMArena German | 1398 | — |
| LMArena Japanese | 1262 | — |
| LMArena Korean | 1313 | — |
| LMArena Spanish | 1403 | — |
Instruction Following MiniMax-M2.7 leads
MiniMax-M2.7: 74.1 (#103), Ministral 8B: 60.5 (#250)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1161 |
Long Context MiniMax-M2.7 leads
MiniMax-M2.7: 43.3 (#99), Ministral 8B: 36.7 (#227)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1419 | 1212 |
Writing & Preference MiniMax-M2.7 leads
MiniMax-M2.7: 58.9 (#112), Ministral 8B: 39.6 (#246)
| Benchmark | MiniMax-M2.7 | Ministral 8B |
|---|---|---|
| LMArena Text | 1405 | 1191 |
| LMArena Creative Writing | 1354 | 1175 |
| LMArena Multi-Turn | 1412 | 1166 |
Frequently asked questions
Is MiniMax-M2.7 better than Ministral 8B?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 28.2 on the Noometry Index. Ministral 8B 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, MiniMax-M2.7 or Ministral 8B?
Ministral 8B is cheaper. It lists at $0.15 per million input tokens and $0.15 per million output tokens; MiniMax-M2.7 lists at $0.30 and $1.20.
Is MiniMax-M2.7 or Ministral 8B better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 35.0 in the Noometry coding category.
Which has the bigger context window?
Ministral 8B does, with 262K tokens against 205K.
How many benchmarks do MiniMax-M2.7 and Ministral 8B share?
13 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Ministral 8B has 17.