Xiaomi, open weights
MiMo-V2.5
MiMo-V2.5 by Xiaomi ranks 93rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.4. Its strongest category is multimodal, where it ranks 54th. API pricing starts at $0.14 per million input tokens and $0.28 per million output tokens, with a 1.05M-token context window.
Last verified
Specifications
- Noometry rank
- #93 of 354
- Index score
- 43.4
- Evidence
- Confirmed 23 results
- Provider
- Xiaomi
- Released
- April 22, 2026
- Weights
- Open weights
- Reasoning
- Yes
- Context window
- 1.05M
- Max output
- 131K
- Input price
- $0.14 / M
- Output price
- $0.28 / M
- Blended price
- $0.18 / M
- Output speed
- Not measured
- Value
- #29 of 219
- Knowledge cutoff
- December 2024
- Input
- text, image, audio, video
- Hugging Face
- XiaomiMiMo/MiMo-V2.5
Category scores
Each category score combines every public result we have in that category.
- Coding 43.9
- Reasoning 28.6
- Math 36.8
- Knowledge 40.8
- Multimodal 39.8
- Multilingual 51.9
- Instruction Following 75.5
- Long Context 44.2
- Writing & Preference 61.6
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 43.9 | #81 | 3 |
| Reasoning | 28.6 | #101 | 2 |
| Math | 36.8 | #163 | 2 |
| Knowledge | 40.8 | #115 | 1 |
| Multimodal | 39.8 | #54 | 1 |
| Multilingual | 51.9 | #99 | 1 |
| Instruction Following | 75.5 | #60 | 1 |
| Long Context | 44.2 | #73 | 1 |
| Writing & Preference | 61.6 | #86 | 3 |
Strengths and weaknesses
Categories where MiMo-V2.5 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Instruction Following | 75.5 | +4.3 | #60 of 305, top 20% |
| Coding | 43.9 | +5.2 | #81 of 340, top 24% |
| Long Context | 44.2 | +3.2 | #73 of 296, top 25% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Math | 36.8 | +0.2 | #163 of 327, top 50% |
| Multimodal | 39.8 | +1.2 | #54 of 128, top 43% |
| Knowledge | 40.8 | +3.5 | #115 of 314, top 37% |
Closest competitors
The models ranked just above and below MiMo-V2.5. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Kimi K2.5 Instant | #89 | 43.6 | — | — | Compare |
| Gemma 4 31B IT | #90 | 43.5 | $0.15 | 3 | Compare |
| Qwen3 235B-A22B | #91 | 43.5 | $1.22 | 85 | Compare |
| Gemma 4 26B A4B IT | #92 | 43.5 | $0.11 | — | Compare |
| Kimi K2.7 Code | #94 | 43.3 | $1.71 | — | Compare |
| Qwen3-VL 235B-A22B | #95 | 43.2 | $1.22 | — | Compare |
| Seed 2.0 Pro | #96 | 43.2 | $1.13 | — | Compare |
| DeepSeek-V3.1-Terminus | #97 | 43.1 | $0.45 | 30 | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1438 | #60 of 113, top 54% | LMArena | 2026-10-08 | |
| SciCode | 43.1% | #66 of 121, top 55% | Epoch AI | ||
| LMArena Coding | 1469 | #59 of 294, top 21% | LMArena | 2026-10-08 | |
| ALE-Bench | 513.95 | #85 of 105, top 81% | Epoch AI |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| CritPt | 3.7% | #61 of 134, top 46% | Epoch AI | ||
| LMArena Hard Prompts | 1450 | #62 of 297, top 21% | LMArena | 2026-10-08 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| ProofBench | 16% | #55 of 77, top 72% | Epoch AI | ||
| LMArena Math | 1436 | #77 of 285, top 28% | LMArena | 2026-10-08 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Expert | 1460 | #63 of 273, top 24% | LMArena | 2026-10-08 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Vision | 1247 | #57 of 122, top 47% | LMArena | 2026-10-09 |
Multilingual
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Non-English | 1404 | #99 of 297, top 34% | LMArena | 2026-10-08 | |
| LMArena Chinese | 1468 | #77 of 285, top 28% | LMArena | 2026-10-08 | |
| LMArena French | 1447 | #75 of 223, top 34% | LMArena | 2026-10-08 | |
| LMArena German | 1421 | #76 of 231, top 33% | LMArena | 2026-10-08 | |
| LMArena Japanese | 1306 | #119 of 211, top 57% | LMArena | 2026-10-08 | |
| LMArena Korean | 1363 | #90 of 213, top 43% | LMArena | 2026-10-08 | |
| LMArena Russian | 1395 | #109 of 283, top 39% | LMArena | 2026-10-08 | |
| LMArena Spanish | 1416 | #97 of 226, top 43% | LMArena | 2026-10-08 |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Instruction Following | 1434 | #56 of 298, top 19% | LMArena | 2026-10-08 |
Long Context
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Longer Query | 1445 | #60 of 291, top 21% | LMArena | 2026-10-08 |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena Text | 1428 | #82 of 297, top 28% | LMArena | 2026-10-08 | |
| LMArena Creative Writing | 1393 | #90 of 295, top 31% | LMArena | 2026-10-08 | |
| LMArena Multi-Turn | 1445 | #63 of 295, top 22% | LMArena | 2026-10-08 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| deepinfra | $0.14 | $0.28 | $0.0028 | 2026-10-10 |
| openrouter | $0.14 | $0.28 | $0.0028 | 2026-10-10 |
| xiaomi | $0.14 | $0.28 | $0.0028 | 2026-10-10 |
Compare MiMo-V2.5
- MiMo-V2.5 vs Gemma 4 26B A4B IT
- MiMo-V2.5 vs Kimi K2.7 Code
- MiMo-V2.5 vs Qwen3 235B-A22B
- MiMo-V2.5 vs Qwen3-VL 235B-A22B
- MiMo-V2.5 vs Gemma 4 31B IT
- MiMo-V2.5 vs Seed 2.0 Pro
- MiMo-V2.5 vs GPT-6 Astra
- MiMo-V2.5 vs Claude Fable 5.1
- MiMo-V2.5 vs Gemini 3.8 Flash
- MiMo-V2.5 vs Kimi K3
- MiMo-V2.5 vs Grok 4.6
- MiMo-V2.5 vs Qwen3.8 Max
- MiMo-V2.5 vs GLM-5.3
- MiMo-V2.5 vs Muse Spark 1.3
Other Xiaomi models
Frequently asked questions
How good is MiMo-V2.5?
MiMo-V2.5 by Xiaomi ranks 93rd of 354 ranked models on the Noometry Index as of October 2026, with a score of 43.4. Its strongest category is multimodal, where it ranks 54th. API pricing starts at $0.14 per million input tokens and $0.28 per million output tokens, with a 1.05M-token context window.
How much does MiMo-V2.5 cost?
MiMo-V2.5 costs $0.14 per million input tokens and $0.28 per million output tokens on Xiaomi's own API, with cached input at $0.0028.
What is MiMo-V2.5's context window?
MiMo-V2.5 accepts up to 1.05M tokens of input and can write up to 131K tokens in one response.
Is MiMo-V2.5 open source?
Yes. MiMo-V2.5's weights are downloadable from Hugging Face (XiaomiMiMo/MiMo-V2.5); check the license for commercial terms.
What are MiMo-V2.5's strengths and weaknesses?
Relative to other ranked models, MiMo-V2.5 places best in instruction following, coding, long context and lowest in math, multimodal, knowledge.
What is MiMo-V2.5 best at?
Its best category is multimodal, where it ranks 54th on Noometry.