MiMo-V2.5-Pro
Xiaomi · released Apr 22, 2026
MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro....
Specification
- Context window
- 1.05M
- Max output
- 131K
- Knowledge cutoff
- Not stated
- Parameters
- 1023.2B
- Licence
- mit
- Serving providers
- 7
- Moderated
- No
- Uptime
- 100.0%
Intelligence
42.9
91th percentile
Coding
60.2
Coding Index
Agentic
29.5
Agentic Index
Output speed
73 t/s
Median across providers
Latency
479ms
Time to first token
Cost per task
$0.09
Estimated
Benchmarks
Where the score comes from
The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.
Evaluation scores
Percentage correct · higher is better
- τ²-bench (Telecom)94.2%
- GPQA Diamond86.6%
- IFBench79.9%
- AA-LCR (long context)77.7%
- SciCode50.2%
- Terminal-Bench Hard43.2%
- Humanity's Last Exam35.7%
An evaluation missing from this list was not run for this model — it is not a zero.
View as table
| Evaluation | Score |
|---|---|
| τ²-bench (Telecom) | 94.2% |
| GPQA Diamond | 86.6% |
| IFBench | 79.9% |
| AA-LCR (long context) | 77.7% |
| SciCode | 50.2% |
| Terminal-Bench Hard | 43.2% |
| Humanity's Last Exam | 35.7% |
Against its peers
Intelligence Index · this model highlighted, nearest peers in grey
- GPT-5.2OpenAI43.3
- Kimi K2.7 CodeMoonshot AI43.0
- MiMo-V2.5-ProXiaomi42.9
- InklingThinking Machines42.3
- Hy3Tencent42.2
- Nex-N2-ProNex AGI41.7
- Inkling SmallThinking Machines41.2
- GPT-5.2-CodexOpenAI41.2
Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.
View as table
| Model | Intelligence |
|---|---|
| GPT-5.2 | 43.3 |
| Kimi K2.7 Code | 43.0 |
| MiMo-V2.5-Pro | 42.9 |
| Inkling | 42.3 |
| Hy3 | 42.2 |
| Nex-N2-Pro | 41.7 |
| Inkling Small | 41.2 |
| GPT-5.2-Codex | 41.2 |
Percentile among all indexed models
Pricing
What it costs to run
List prices per million tokens, plus what one representative task works out to.
List price
- Input / 1M tokens
- $0.435
- Output / 1M tokens
- $0.87
- Cached input / 1M
- $0.004
- Blended 3:1
- $0.544
One task, estimated
$0.09
- Input tokens
- 50,000
- Output tokens
- 80,000
- Profile
- Reasoning
Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).
Serving providers
Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.
Arena
Head-to-head generation quality
Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.
- Overall Elo
- 1,314
- Win rate
- 58.7%
- Strongest at
- Game development
- Tournaments
- 2,262
Elo by category
Dot position on a 1,200–1,325 scale · Elo has no meaningful zero
- 1,314
- 1,305
- 1,300
- 1,296
- 1,291
- 1,223
Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.
View as table
| Category | Elo | Win rate |
|---|---|---|
| Game development | 1314 | 58.7% |
| 3D scenes | 1305 | 56.9% |
| Websites | 1300 | 55.8% |
| Data visualisation | 1296 | 54.7% |
| UI components | 1291 | 55.2% |
| SVG | 1223 | 52.0% |