Model comparison
MiMo-V2.5 vs Mistral Small 3
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 31.2 on the Noometry Index. Mistral Small 3 costs 3.0× less per token, which makes it the better buy when MiMo-V2.5's lead doesn't matter for your workload.
Last verified . 16 shared benchmarks.
Mistral AISummary
- They share 16 benchmarks with published results for both. MiMo-V2.5 scores higher in 8 categories and Mistral Small 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2.5 leads 61.6 to 32.2.
- Mistral Small 3 is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.14 / $0.28 for MiMo-V2.5.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 33K.
Side by side
| MiMo-V2.5 | Mistral Small 3 | |
|---|---|---|
| Provider | Xiaomi | Mistral AI |
| Noometry Index | 43.4 | 31.2 |
| Released | 2026-04-22 | 2025-01-30 |
| Weights | Open | Open |
| Context window | 1.05M | 33K |
| Max output | 131K | 16K |
| Input $ / M tokens | $0.14 | $0.05 |
| Output $ / M tokens | $0.28 | $0.08 |
| Results tracked | 23 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2.5 leads
MiMo-V2.5: 43.9 (#81), Mistral Small 3: 36.5 (#207)
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Coding | 1469 | 1246 |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| BigCodeBench Instruct | — | 45.3% |
| BigCodeBench Complete | — | 50.4% |
| ALE-Bench | 513.95 | — |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Mistral Small 3: 18.9 (#273)
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1233 |
| CritPt | 3.7% | — |
| Chess Puzzles | — | 0% |
| Epoch Capabilities Index | — | 127.07 |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Mistral Small 3: 16.3 (#295)
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Math | 1436 | 1240 |
| OTIS Mock AIME 2024-2025 | — | 6.7% |
| ProofBench | 16% | — |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), Mistral Small 3: 25.1 (#263)
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Expert | 1460 | 1202 |
| GPQA Diamond | — | 47.3% |
| Confabulations | — | 25.2% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Mistral Small 3: —
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Mistral Small 3: 37.3 (#236)
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Non-English | 1404 | 1198 |
| LMArena Chinese | 1468 | 1204 |
| LMArena French | 1447 | 1203 |
| LMArena German | 1421 | 1211 |
| LMArena Japanese | 1306 | 1111 |
| LMArena Korean | 1363 | 1188 |
| LMArena Russian | 1395 | 1216 |
| LMArena Spanish | 1416 | — |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Mistral Small 3: 63.7 (#229)
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Instruction Following | 1434 | 1214 |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Mistral Small 3: 37.8 (#211)
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Longer Query | 1445 | 1246 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Mistral Small 3: 32.2 (#280)
| Benchmark | MiMo-V2.5 | Mistral Small 3 |
|---|---|---|
| LMArena Text | 1428 | 1234 |
| LMArena Creative Writing | 1393 | 1195 |
| LMArena Multi-Turn | 1445 | 1217 |
| EQ-Bench Creative Writing | — | 707 |
Frequently asked questions
Is MiMo-V2.5 better than Mistral Small 3?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 31.2 on the Noometry Index. Mistral Small 3 costs 3.0× less per token, which makes it the better buy when MiMo-V2.5's lead doesn't matter for your workload.
Which is cheaper, MiMo-V2.5 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; MiMo-V2.5 lists at $0.14 and $0.28.
Is MiMo-V2.5 or Mistral Small 3 better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 36.5 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 33K.
How many benchmarks do MiMo-V2.5 and Mistral Small 3 share?
16 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Mistral Small 3 has 24.