elorian/glimpse
Elorianvia OpenRouter- average±4.2 (95%)
- 79.0
- leaderboard rankof 114
- ≈25
- benchmarksof 12
- 12
- per 1,000 documentsmean over its benchmarks
- $27
- seconds per inputmean response time
- 61.5
By task
-
Data correction
73.8
Best of 114 models with all its benchmarks: claude-opus-5-5, 82.7.
-
Document understanding
91.0
Best of 107 models with all its benchmarks: gpt-6-astra, 97.0.
-
Information extraction
82.3
Best of 107 models with all its benchmarks: grok-4.6, 90.8.
-
Transcription
75.5
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 | 93.0±7.8 | ≈57of 115 | $24$0.12 run | 33.02 | T2138 · 24 Oct 2026prompt_v2.txt |
| Blacklist Cards | 89.8±6.2 | ≈51of 114 | $17$0.57 run | 41.8 | T2145 · 24 Oct 2026prompt.txt |
| Book Advert XML Repairother prompt | 51.8±11.9 | ≈16of 119 | $28$1.38 run | 86.74 | T2147 · 24 Oct 2026prompt_v2.txt |
| Business Letters | 57.0±7.1 | ≈65of 114 | $21$1.17 run | 48.13 | T2139 · 24 Oct 2026prompt.txt |
| Company Listsother prompt | 91.4±6.8 | ≈6of 114 | $19$0.29 run | 42.63 | T2146 · 24 Oct 2026prompt_v2.txt |
| Duty Rosters | 82.8±5.4 | ≈30of 107 | $52$1.10 run | 110.06 | T2151 · 24 Oct 2026prompt.txt |
| Fraktur Adverts | 77.0±37.7 | ≈32of 114 | $43$0.22 run | 95.32 | T2142 · 24 Oct 2026prompt_optimized.txt |
| General Meeting Minutes | 76.1±16.3 | ≈25of 108 | $30$0.27 run | 85.82 | T2150 · 24 Oct 2026prompt.txt |
| Library Cardsother prompt | 86.0±2.2 | ≈51of 114 | $16$4.23 run | 40.81 | T2143 · 24 Oct 2026prompt_year-string.txt |
| Magazine Pagesother prompt | 94.2±4.0 | ≈1of 115 | $10$0.46 run | 19.37 | T2149 · 24 Oct 2026prompt_explicit-json.txt |
| Medieval Manuscripts | 53.6±20.7 | ≈93of 114 | $43$0.52 run | 97.24 | T2144 · 24 Oct 2026prompt.txt |
| Personnel Cards | 95.9±4.1 | ≈30of 114 | $16$0.98 run | 37.23 | T2148 · 24 Oct 2026prompt.txt |
Price
| From | Input, $ per million tokens | Output, $ per million tokens | Source |
|---|---|---|---|
| 24 Oct 2026 | 0.6 | 3.0 | archived price page |
Every run
- T2151Duty Rosters24 Oct 202682.8$1.10
- T2150General Meeting Minutes24 Oct 202676.1$0.27
- T2149Magazine Pages24 Oct 202694.2$0.46
- T2148Personnel Cards24 Oct 202695.9$0.98
- T2147Book Advert XML Repair24 Oct 202651.8$1.38
- T2146Company Lists24 Oct 202691.4$0.29
- T2145Blacklist Cards24 Oct 202689.8$0.57
- T2144Medieval Manuscripts24 Oct 202653.6$0.52
- T2143Library Cards24 Oct 202686.0$4.23
- T2142Fraktur Adverts24 Oct 202677.0$0.22
- T2141Business Letters24 Oct 2026 · 32 signed letters61.0$0.50
- T2140Business Letters24 Oct 2026 · 25 unsigned letters55.0$0.43
- T2139Business Letters24 Oct 2026 · all 57 letters57.0$1.17
- T2138Bibliographic Data24 Oct 202693.0$0.12