Model comparison
MiniMax-M2.5 vs Mistral Small 3
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 9.1× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
MiniMax
Mistral AISummary
- They share 18 benchmarks with published results for both. MiniMax-M2.5 scores higher in 6 categories and Mistral Small 3 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.5 leads 53.9 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M2.5.
- MiniMax-M2.5 accepts more context: 205K tokens versus 33K.
Side by side
| MiniMax-M2.5 | Mistral Small 3 | |
|---|---|---|
| Provider | MiniMax | Mistral AI |
| Noometry Index | 38.3 | 31.2 |
| Released | 2026-02-12 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 205K | 33K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.30 | $0.05 |
| Output $ / M tokens | $1.20 | $0.08 |
| Results tracked | 33 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 48.1 (#58), Mistral Small 3: 36.5 (#207)
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1381 | 1246 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), Mistral Small 3: —
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Mistral Small 3 leads
MiniMax-M2.5: 17.5 (#292), Mistral Small 3: 18.9 (#273)
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1233 |
| Epoch Capabilities Index | 146.68 | 127.07 |
| ARC-AGI-2 | 4.9% | — |
| Kagi LLM Benchmark | 55.2% | — |
| NYT Connections (extended) | 16.8% | — |
| ARC-AGI-1 | 63.7% | — |
| Chess Puzzles | — | 0% |
Math MiniMax-M2.5 leads
MiniMax-M2.5: 26.9 (#253), Mistral Small 3: 16.3 (#295)
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1378 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| ProofBench | 4% | — |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), Mistral Small 3: 25.1 (#263)
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1379 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
| Vectara Hallucination Rate | 9.1% | — |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.1 (#152), Mistral Small 3: 37.3 (#236)
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1338 | 1198 |
| LMArena Chinese | 1393 | 1204 |
| LMArena French | 1362 | 1203 |
| LMArena German | 1362 | 1211 |
| LMArena Japanese | 1171 | 1111 |
| LMArena Korean | 1232 | 1188 |
| LMArena Russian | 1358 | 1216 |
| LMArena Spanish | 1354 | — |
Instruction Following MiniMax-M2.5 leads
MiniMax-M2.5: 71.5 (#148), Mistral Small 3: 63.7 (#229)
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1353 | 1214 |
Long Context Too close to call
MiniMax-M2.5: 37.5 (#216), Mistral Small 3: 37.8 (#211)
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1366 | 1246 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 53.9 (#153), Mistral Small 3: 32.2 (#280)
| Benchmark | MiniMax-M2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1359 | 1234 |
| LMArena Creative Writing | 1331 | 1195 |
| EQ-Bench Creative Writing | 1361 | 707 |
| LMArena Multi-Turn | 1364 | 1217 |
Frequently asked questions
Is MiniMax-M2.5 better than Mistral Small 3?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 31.2 on the Noometry Index. Mistral Small 3 costs 9.1× less per token, which makes it the better buy when MiniMax-M2.5's lead doesn't matter for your workload.
Which is cheaper, MiniMax-M2.5 or Mistral Small 3?
Mistral Small 3 is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; MiniMax-M2.5 lists at $0.30 and $1.20.
Is MiniMax-M2.5 or Mistral Small 3 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
MiniMax-M2.5 does, with 205K tokens against 33K.
How many benchmarks do MiniMax-M2.5 and Mistral Small 3 share?
18 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Mistral Small 3 has 24.