meta/muse-wonder
Metavia OpenRouter- average±2.9 (95%)
- 84.5
- leaderboard rankof 114
- ≈14
- benchmarksof 12
- 12
- per 1,000 documentsmean over its benchmarks
- $65
- seconds per inputmean response time
- 19.1
By task
-
Data correction
73.8
Best of 114 models with all its benchmarks: claude-opus-5-5, 82.7.
-
Document understanding
91.2
Best of 107 models with all its benchmarks: gpt-6-astra, 97.0.
-
Information extraction
84.2
Best of 107 models with all its benchmarks: grok-4.6, 90.8.
-
Transcription
93.0
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 | 77.7±25.3 | ≈91of 115 | $89$0.44 run | 17.59 | T2040 · 24 Oct 2026prompt_v2.txt |
| Blacklist Cards | 97.5±1.8 | ≈1of 114 | $31$1.01 run | 6.91 | T2047 · 24 Oct 2026prompt.txt |
| Book Advert XML Repairother prompt | 49.9±10.7 | ≈16of 119 | $74$3.72 run | 20.83 | T2049 · 24 Oct 2026prompt_v2.txt |
| Business Letters | 62.0±6.6 | ≈24of 114 | $54$3.09 run | 15.46 | T2041 · 24 Oct 2026prompt.txt |
| Company Listsother prompt | 90.5±12.4 | ≈6of 114 | $54$0.81 run | 12.27 | T2048 · 24 Oct 2026prompt_v2.txt |
| Duty Rosters | 80.0±9.9 | ≈30of 107 | $157$3.29 run | 69.38 | T2053 · 24 Oct 2026prompt.txt |
| Fraktur Adverts | 96.7±3.9 | ≈27of 114 | $103$0.52 run | 23.13 | T2044 · 24 Oct 2026prompt_optimized.txt |
| General Meeting Minutes | 91.4±4.9 | ≈1of 108 | $52$0.47 run | 13.85 | T2052 · 24 Oct 2026prompt.txt |
| Library Cardsother prompt | 90.3±1.5 | ≈1of 114 | $30$8.00 run | 8.38 | T2045 · 24 Oct 2026prompt_year-string.txt |
| Magazine Pagesother prompt | 96.0±3.1 | ≈1of 115 | $30$1.36 run | 8.35 | T2051 · 24 Oct 2026prompt_explicit-json.txt |
| Medieval Manuscripts | 84.5±9.6 | ≈1of 114 | $63$0.76 run | 21.94 | T2046 · 24 Oct 2026prompt.txt |
| Personnel Cards | 97.7±0.9 | ≈1of 114 | $48$2.93 run | 10.58 | T2050 · 24 Oct 2026prompt.txt |
Price
| From | Input, $ per million tokens | Output, $ per million tokens | Source |
|---|---|---|---|
| 24 Oct 2026 | 4.0 | 20.0 | archived price page |
Every run
- T2053Duty Rosters24 Oct 202680.0$3.29
- T2052General Meeting Minutes24 Oct 202691.4$0.47
- T2051Magazine Pages24 Oct 202696.0$1.36
- T2050Personnel Cards24 Oct 202697.7$2.93
- T2049Book Advert XML Repair24 Oct 202649.9$3.72
- T2048Company Lists24 Oct 202690.5$0.81
- T2047Blacklist Cards24 Oct 202697.5$1.01
- T2046Medieval Manuscripts24 Oct 202684.5$0.76
- T2045Library Cards24 Oct 202690.3$8.00
- T2044Fraktur Adverts24 Oct 202696.7$0.52
- T2043Business Letters24 Oct 2026 · 32 signed letters66.0$1.75
- T2042Business Letters24 Oct 2026 · 25 unsigned letters58.0$0.88
- T2041Business Letters24 Oct 2026 · all 57 letters62.0$3.09
- T2040Bibliographic Data24 Oct 202677.7$0.44