Quality
Highest overall scores
- 1
Xiaomi: MiMo-V2.5-Pro42.2 - 2Xiaomi: MiMo-V2.537.2
Xiaomi model benchmarks.
Compare Xiaomi models across answer quality, coding, complex tasks, speed, price, and context size.
Response speed
Fastest output in this sample
- 1Xiaomi: MiMo-V2.5-Pro68 t/s
- 2Xiaomi: MiMo-V2.555 t/s
Input price
Lowest price per 1M tokens
- 1Xiaomi: MiMo-V2.5$0.14/1M
- 2Xiaomi: MiMo-V2.5-Pro$0.43/1M
Highlights
Quality
Overall capability · Higher is better
Speed
Output tokens per second · Higher is better
Input price
USD per 1M tokens · Lower is better
Quality benchmarks
Compare Xiaomi model capability.
Performance and price
Compare practical tradeoffs.
All Xiaomi models.
2 models in the current catalogue.
| Model | Links | |||||
|---|---|---|---|---|---|---|
| Xiaomi: MiMo-V2.5-Pro | 42.2 | 68 t/s | 1.1M | $0.43 | $0.87 | |
| Xiaomi: MiMo-V2.5 | 37.2 | 55 t/s | 1.1M | $0.14 | $0.28 |
Xiaomi technical benchmarks.
Compare named evaluation records available for Xiaomi models. Missing results remain blank rather than being estimated.
| Benchmark | Area | MiMo-V2.5-Pro | MiMo-V2.5 | Source |
|---|---|---|---|---|
| Intelligence Index | overallQuality | 42.2 | 37.2 | OpenRouter / artificial-analysis |
| Coding Index | coding | 60.2 | 56.8 | OpenRouter / artificial-analysis |
| Agentic Index | agentic | 29.1 | 23.7 | OpenRouter / artificial-analysis |
| GPQA | GPQA Diamond | 86.6 | 84.9 | OpenRouter model benchmarks |
| Humanity's Last Exam | HLE | 33.8 | 25.2 | OpenRouter model benchmarks |
| IFBench | IFBench | 79.9 | 67.1 | OpenRouter model benchmarks |
| τ²-Bench Telecom | τ²-Bench Telecom | 94.2 | 90.6 | OpenRouter model benchmarks |
| AA-LCR | AA-LCR | 73.3 | 62.7 | OpenRouter model benchmarks |
| GDPval-AA | GDPval-AA | 38.3 | 32.2 | OpenRouter model benchmarks |
| CritPt | CritPt | 4 | 3.7 | OpenRouter model benchmarks |
| SciCode | SciCode | 50.2 | 43.1 | OpenRouter model benchmarks |
| Terminal-Bench Hard | Terminal-Bench Hard | 43.2 | 41.7 | OpenRouter model benchmarks |
| AA-Omniscience Accuracy | AA-Omniscience Accuracy | 22.6 | 17.3 | OpenRouter model benchmarks |
| AA-Omniscience Non-Hallucination Rate | AA-Omniscience Non-Hallucination Rate | 75.5 | 67.8 | OpenRouter model benchmarks |