gpt-5.1-2025-11-13
OpenAI- average±3.3 (95%)
- 70.1
- leaderboard rankof 114
- ≈63
- benchmarksof 12
- 12
- per 1,000 documentsmean over its benchmarks
- $8.94
- seconds per inputmean response time
- 12.1
By task
-
Data correction
55.8
Best of 114 models with all its benchmarks: claude-opus-5-5, 82.7.
-
Document understanding
73.9
Best of 107 models with all its benchmarks: gpt-6-astra, 97.0.
-
Information extraction
80.4
Best of 107 models with all its benchmarks: grok-4.6, 90.8.
-
Transcription
67.2
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 Data | 97.5±1.4 | ≈8of 115 | $22$0.11 run | 22.5 | T0403 · 25 Jan 2026prompt.txt |
| Blacklist Cards | 89.7±3.9 | ≈51of 114 | $2.78$0.092 run | 4.4 | T0410 · 25 Jan 2026prompt.txt |
| Book Advert XML Repair | 20.4±7.1 | ≈64of 119 | $8.45$0.42 run | 9.22 | T0454 · 9 Dec 2025prompt.txt |
| Business Letters | 56.0±6.7 | ≈75of 114 | $3.17$0.18 run | 4.91 | T0404 · 25 Jan 2026prompt.txt |
| Company Lists | 80.7±11.6 | ≈58of 114 | $7.60$0.11 run | 7.3 | T0411 · 25 Nov 2025prompt.txt |
| Duty Rosters | 74.3±3.3 | ≈64of 107 | $15$0.31 run | 10.83 | T1301 · 24 Jul 2026prompt.txt |
| Fraktur Adverts | 44.9±29.5 | ≈94of 114 | $18$0.088 run | 37.36 | T0407 · 25 Jan 2026prompt_optimized.txt |
| General Meeting Minutes | 80.1±10.2 | ≈25of 108 | $7.13$0.064 run | 7.3 | T1252 · 3 Jul 2026prompt.txt |
| Library Cards | 84.2±1.5 | ≈51of 114 | $7.14$1.88 run | 18.76 | T0408 · 25 Jan 2026prompt.txt |
| Magazine Pages | 56.3±12.9 | ≈47of 115 | $1.94$0.089 run | 4.0 | T0794 · 23 Mar 2026prompt.txt |
| Medieval Manuscripts | 65.6±13.8 | ≈72of 114 | $4.15$0.050 run | 8.5 | T0409 · 26 Jan 2026prompt.txt |
| Personnel Cards | 91.1±2.9 | ≈78of 114 | $10$0.61 run | 9.7 | T0613 · 9 Feb 2026prompt.txt |
Price
| From | Input, $ per million tokens | Output, $ per million tokens | Source |
|---|---|---|---|
| 2 Mar 2026 | 1.25 | 10.0 | archived price page |
Every run
- T1301Duty Rosters16 Sep 202673.3$0.31
- T1252General Meeting Minutes16 Sep 202674.4$0.063
- T0794Magazine Pages16 Sep 202656.2$0.088
- T1301Duty Rosters24 Jul 202674.3$0.31
- T1252General Meeting Minutes3 Jul 202680.1$0.064
- T0794Magazine Pages23 Mar 202656.3$0.089
- T0613Personnel Cards10 Feb 202689.3$0.61
- T0613Personnel Cards9 Feb 202691.1$0.61
- T0454Book Advert XML Repair26 Jan 202620.1$0.42
- T0409Medieval Manuscripts26 Jan 202665.6$0.050
- T0412Company Lists25 Jan 202661.1$0.12
- T0411Company Lists25 Jan 202679.9$0.11
- T0410Blacklist Cards25 Jan 202689.7$0.092
- T0408Library Cards25 Jan 202684.2$1.88
- T0407Fraktur Adverts25 Jan 202644.9$0.088
- T0406Business Letters25 Jan 2026 · 32 signed letters60.0$0.11
- T0405Business Letters25 Jan 2026 · 25 unsigned letters51.0$0.070
- T0404Business Letters25 Jan 2026 · all 57 letters56.0$0.18
- T0403Bibliographic Data25 Jan 202697.5$0.11
- T0454Book Advert XML Repair9 Dec 202520.4$0.42
- T0454Book Advert XML Repair8 Dec 202520.0$0.41
- T0412Company Lists25 Nov 202567.2$0.12
- T0411Company Lists25 Nov 202580.7$0.11
- T0410Blacklist Cards25 Nov 202582.1$0.092
- T0409Medieval Manuscripts25 Nov 202565.1$0.048
- T0408Library Cards25 Nov 202581.8$0.79
- T0407Fraktur Adverts25 Nov 202533.0$0.089
- T0406Business Letters25 Nov 2025 · 32 signed letters59.0$0.11
- T0405Business Letters25 Nov 2025 · 25 unsigned letters54.0$0.070
- T0404Business Letters25 Nov 2025 · all 57 letters54.0$0.18
- T0403Bibliographic Data25 Nov 202578.9$0.093