Model comparison
MiMo-V2.5 vs Mixtral 8x7B
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 27.1 on the Noometry Index.
Last verified . 17 shared benchmarks.
Mistral AISummary
- They share 17 benchmarks with published results for both. MiMo-V2.5 scores higher in 8 categories and Mixtral 8x7B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiMo-V2.5 leads 40.8 to 11.0.
- MiMo-V2.5 is cheaper at $0.14 / $0.28 per million input/output tokens, against $0.70 / $0.70 for Mixtral 8x7B.
- MiMo-V2.5 accepts more context: 1.05M tokens versus 32K.
Side by side
| MiMo-V2.5 | Mixtral 8x7B | |
|---|---|---|
| Provider | Xiaomi | Mistral AI |
| Noometry Index | 43.4 | 27.1 |
| Released | 2026-04-22 | 2023-12-11 |
| Weights | Open | Open |
| Context window | 1.05M | 32K |
| Max output | 131K | 32K |
| Input $ / M tokens | $0.14 | $0.70 |
| Output $ / M tokens | $0.28 | $0.70 |
| Results tracked | 23 | 38 |
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), Mixtral 8x7B: 32.8 (#269)
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Coding | 1469 | 1126 |
| LMArena WebDev | 1438 | — |
| SciCode | 43.1% | — |
| ALE-Bench | 513.95 | — |
| HumanEval+ | — | 39.6% |
| MBPP+ | — | 49.7% |
Reasoning MiMo-V2.5 leads
MiMo-V2.5: 28.6 (#101), Mixtral 8x7B: 18.2 (#285)
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Hard Prompts | 1450 | 1115 |
| CritPt | 3.7% | — |
| DTBench | — | 49.6% |
| Adversarial NLI | — | 55.2% |
| Epoch Capabilities Index | — | 118.47 |
| ForecastBench | — | 56.3 |
| HellaSwag | — | 86.7% |
| PIQA | — | 83.6% |
| WinoGrande | — | 77.2% |
Math MiMo-V2.5 leads
MiMo-V2.5: 36.8 (#163), Mixtral 8x7B: 18.8 (#289)
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Math | 1436 | 1147 |
| ProofBench | 16% | — |
| Omni-MATH | — | 10.5% |
| MATH Level 5 | — | 10% |
| GSM8K | — | 74.4% |
Knowledge MiMo-V2.5 leads
MiMo-V2.5: 40.8 (#115), Mixtral 8x7B: 11.0 (#301)
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Expert | 1460 | 1088 |
| GPQA Diamond | — | 30.6% |
| MMLU-Pro | — | 33.5% |
| GPQA (HELM) | — | 29.6% |
| ARC (AI2) Challenge | — | 87.3% |
| MMLU | — | 70.6% |
| OpenBookQA | — | 85.8% |
| TriviaQA | — | 82.2% |
Multimodal Not comparable
MiMo-V2.5: 39.8 (#54), Mixtral 8x7B: —
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Vision | 1247 | — |
Multilingual MiMo-V2.5 leads
MiMo-V2.5: 51.9 (#99), Mixtral 8x7B: 29.6 (#266)
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Non-English | 1404 | 1077 |
| LMArena Chinese | 1468 | 1055 |
| LMArena French | 1447 | 1166 |
| LMArena German | 1421 | 1114 |
| LMArena Japanese | 1306 | 931 |
| LMArena Korean | 1363 | 968 |
| LMArena Russian | 1395 | 1090 |
| LMArena Spanish | 1416 | 1111 |
Instruction Following MiMo-V2.5 leads
MiMo-V2.5: 75.5 (#60), Mixtral 8x7B: 51.0 (#297)
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Instruction Following | 1434 | 1109 |
| IFEval | — | 57.5% |
Long Context MiMo-V2.5 leads
MiMo-V2.5: 44.2 (#73), Mixtral 8x7B: 33.4 (#260)
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Longer Query | 1445 | 1103 |
Writing & Preference MiMo-V2.5 leads
MiMo-V2.5: 61.6 (#86), Mixtral 8x7B: 34.2 (#270)
| Benchmark | MiMo-V2.5 | Mixtral 8x7B |
|---|---|---|
| LMArena Text | 1428 | 1132 |
| LMArena Creative Writing | 1393 | 1109 |
| LMArena Multi-Turn | 1445 | 1115 |
| WildBench | — | 67.3% |
Frequently asked questions
Is MiMo-V2.5 better than Mixtral 8x7B?
MiMo-V2.5 is the stronger model overall, scoring 43.4 to 27.1 on the Noometry Index.
Which is cheaper, MiMo-V2.5 or Mixtral 8x7B?
MiMo-V2.5 is cheaper. It lists at $0.14 per million input tokens and $0.28 per million output tokens; Mixtral 8x7B lists at $0.70 and $0.70.
Is MiMo-V2.5 or Mixtral 8x7B better for coding?
MiMo-V2.5 scores higher on coding benchmarks: 43.9 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
MiMo-V2.5 does, with 1.05M tokens against 32K.
How many benchmarks do MiMo-V2.5 and Mixtral 8x7B share?
17 benchmarks have published results for both models. MiMo-V2.5 has 23 scored results on Noometry and Mixtral 8x7B has 38.