xiaomi/mimo-v2.6-pro
Xiaomivia OpenRouter- average±5.1 (95%)
- 61.8
- leaderboard rankof 114
- ≈89
- benchmarksof 12
- 12
- per 1,000 documentsmean over its benchmarks
- $6.03
- seconds per inputmean response time
- 139.1
By task
-
Data correction
40.0
Best of 114 models with all its benchmarks: claude-opus-5-5, 82.7.
-
Document understanding
47.1
Best of 107 models with all its benchmarks: gpt-6-astra, 97.0.
-
Information extraction
77.0
Best of 107 models with all its benchmarks: grok-4.6, 90.8.
-
Transcription
39.8
Best of 114 models with all its benchmarks: gemini-4-argon, 96.2.
By benchmark
| Benchmark | ScoreThe best current run on each benchmark, on the benchmark's metric scaled to 0–100. ± is the 95% sampling margin, from resampling the run's inputs. | RankRank among all current models on that benchmark; ≈ for models that cannot be told apart within sampling error. | Per 1,000 docs | s / input | Best run |
|---|---|---|---|---|---|
| Bibliographic Dataother prompt | 81.8±20.7 | ≈91of 115 | $5.21$0.026 run | 43.86 | T2082 · 25 Oct 2026prompt_v2.txt |
| Blacklist Cards | 86.2±8.2 | ≈87of 114 | $2.70$0.089 run | 39.74 | T2089 · 25 Oct 2026prompt.txt |
| Book Advert XML Repairother prompt | 48.8±11.1 | ≈16of 119 | $4.25$0.21 run | 81.63 | T2091 · 25 Oct 2026prompt_v2.txt |
| Business Letters | 59.0±6.8 | ≈24of 114 | $4.45$0.25 run | 44.87 | T2083 · 25 Oct 2026prompt.txt |
| Company Listsother prompt | 77.5±17.2 | ≈58of 114 | $7.45$0.11 run | 98.2 | T2090 · 25 Oct 2026prompt_v2.txt |
| Duty Rosters | 75.8±5.6 | ≈46of 107 | $15$0.32 run | 247.78 | T2095 · 25 Oct 2026prompt.txt |
| Fraktur Adverts | 53.0±42.8 | ≈67of 114 | $11$0.053 run | 469.21 | T2086 · 25 Oct 2026prompt_optimized.txt |
| General Meeting Minutes | 73.5±14.2 | ≈85of 108 | $8.47$0.076 run | 169.96 | T2094 · 25 Oct 2026prompt.txt |
| Library Cardsother prompt | 85.1±1.5 | ≈51of 114 | $1.12$0.29 run | 24.1 | T2087 · 25 Oct 2026prompt_year-string.txt |
| Magazine Pagesother prompt | 34.3±13.3 | ≈56of 115 | $2.78$0.13 run | 32.43 | T2093 · 25 Oct 2026prompt_explicit-json.txt |
| Medieval Manuscripts | 35.0±21.8 | ≈95of 114 | $7.60$0.091 run | 380.12 | T2088 · 25 Oct 2026prompt.txt |
| Personnel Cards | 31.3±5.0 | ≈111of 114 | $2.31$0.14 run | 37.38 | T2092 · 25 Oct 2026prompt.txt |
Price
| From | Input, $ per million tokens | Output, $ per million tokens | Source |
|---|---|---|---|
| 24 Oct 2026 | 0.435 | 0.87 | archived price page |
Every run
- T2095Duty Rosters25 Oct 202675.8$0.32
- T2094General Meeting Minutes25 Oct 202673.5$0.076
- T2093Magazine Pages25 Oct 202634.3$0.13
- T2092Personnel Cards25 Oct 202631.3$0.14
- T2091Book Advert XML Repair25 Oct 202648.8$0.21
- T2090Company Lists25 Oct 202677.5$0.11
- T2089Blacklist Cards25 Oct 202686.2$0.089
- T2088Medieval Manuscripts25 Oct 202635.0$0.091
- T2087Library Cards25 Oct 202685.1$0.29
- T2086Fraktur Adverts25 Oct 202653.0$0.053
- T2085Business Letters25 Oct 2026 · 32 signed letters61.0$0.074
- T2084Business Letters25 Oct 2026 · 25 unsigned letters65.0$0.045
- T2083Business Letters25 Oct 2026 · all 57 letters59.0$0.25
- T2082Bibliographic Data25 Oct 202681.8$0.026