xiaomi/mimo-v2.6-flash
Xiaomivia OpenRouter- average±4.9 (95%)
- 62.9
- leaderboard rankof 114
- ≈79
- benchmarksof 12
- 12
- per 1,000 documentsmean over its benchmarks
- $3.18
- seconds per inputmean response time
- 44.7
By task
-
Data correction
55.5
Best of 114 models with all its benchmarks: claude-opus-5-5, 82.7.
-
Document understanding
52.3
Best of 107 models with all its benchmarks: gpt-6-astra, 97.0.
-
Information extraction
72.4
Best of 107 models with all its benchmarks: grok-4.6, 90.8.
-
Transcription
56.6
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 | 66.4±34.0 | ≈103of 115 | $2.41$0.012 run | 21.68 | T2096 · 25 Oct 2026prompt_v2.txt |
| Blacklist Cards | 91.0±3.5 | ≈51of 114 | $0.37$0.012 run | 2.15 | T2103 · 25 Oct 2026prompt.txt |
| Book Advert XML Repairother prompt | 31.3±10.9 | ≈41of 119 | $0.71$0.036 run | 14.16 | T2105 · 25 Oct 2026prompt_v2.txt |
| Business Letters | 61.0±8.2 | ≈24of 114 | $0.89$0.051 run | 20.03 | T2097 · 25 Oct 2026prompt.txt |
| Company Listsother prompt | 89.1±8.9 | ≈6of 114 | $1.55$0.023 run | 9.29 | T2104 · 25 Oct 2026prompt_v2.txt |
| Duty Rosters | 30.7±19.0 | ≈96of 107 | $24$0.50 run | 354.41 | T2109 · 25 Oct 2026prompt.txt |
| Fraktur Adverts | 18.0±35.4 | ≈97of 114 | $4.29$0.021 run | 64.51 | T2100 · 25 Oct 2026prompt_optimized.txt |
| General Meeting Minutes | 83.1±10.4 | ≈25of 108 | $1.06$0.010 run | 11.92 | T2108 · 25 Oct 2026prompt.txt |
| Library Cardsother prompt | 85.7±1.6 | ≈51of 114 | $0.55$0.14 run | 17.95 | T2101 · 25 Oct 2026prompt_year-string.txt |
| Magazine Pagesother prompt | 46.6±12.4 | ≈47of 115 | $0.42$0.019 run | 2.0 | T2107 · 25 Oct 2026prompt_explicit-json.txt |
| Medieval Manuscripts | 72.1±10.8 | ≈27of 114 | $0.46$0.006 run | 6.84 | T2102 · 25 Oct 2026prompt.txt |
| Personnel Cards | 79.6±9.5 | ≈94of 114 | $1.44$0.088 run | 11.48 | T2106 · 25 Oct 2026prompt.txt |
Price
| From | Input, $ per million tokens | Output, $ per million tokens | Source |
|---|---|---|---|
| 24 Oct 2026 | 0.14 | 0.28 | archived price page |
Every run
- T2109Duty Rosters25 Oct 202630.7$0.50
- T2108General Meeting Minutes25 Oct 202683.1$0.010
- T2107Magazine Pages25 Oct 202646.6$0.019
- T2106Personnel Cards25 Oct 202679.6$0.088
- T2105Book Advert XML Repair25 Oct 202631.3$0.036
- T2104Company Lists25 Oct 202689.1$0.023
- T2103Blacklist Cards25 Oct 202691.0$0.012
- T2102Medieval Manuscripts25 Oct 202672.1$0.006
- T2101Library Cards25 Oct 202685.7$0.14
- T2100Fraktur Adverts25 Oct 202618.0$0.021
- T2099Business Letters25 Oct 2026 · 32 signed letters64.0$0.027
- T2098Business Letters25 Oct 2026 · 25 unsigned letters78.0$0.012
- T2097Business Letters25 Oct 2026 · all 57 letters61.0$0.051
- T2096Bibliographic Data25 Oct 202666.4$0.012