University of Basel RISE · Research and Infrastructure SupportHumanities Data Benchmark

claude-opus-5-5

Anthropic
average±1.8 (95%)
89.8
leaderboard rankof 114
≈1
benchmarksof 12
12
per 1,000 documentsmean over its benchmarks
$42
seconds per inputmean response time
12.9
Compare with other models Its row in the Matrix All its test runs

By task

  • Data correction

    82.7

    Best of 114 models with all its benchmarks: claude-opus-5-5, 82.7.

  • Document understanding

    96.7

    Best of 107 models with all its benchmarks: gpt-6-astra, 97.0.

  • Information extraction

    89.9

    Best of 107 models with all its benchmarks: grok-4.6, 90.8.

  • Transcription

    94.6

    Best of 114 models with all its benchmarks: gemini-4-argon, 96.2.

By benchmark

BenchmarkScoreThe 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 docss / inputBest run
Bibliographic Data 98.7±1.2 ≈1of 115 $65$0.32 run 17.97 T1810 · 29 Sep 2026prompt.txt
Blacklist Cards 95.3±2.5 ≈14of 114 $22$0.72 run 5.94 T1817 · 27 Sep 2026prompt.txt
Book Advert XML Repair 67.9±10.3 ≈1of 119 $44$2.22 run 18.33 T1820 · 27 Sep 2026prompt.txt
Business Letters 75.0±7.3 ≈1of 114 $35$1.98 run 6.51 T1811 · 27 Sep 2026prompt.txt
Company Lists 77.7±13.3 ≈58of 114 $49$0.73 run 13.94 T1818 · 27 Sep 2026prompt.txt
Duty Rosters 95.7±1.4 ≈1of 107 $53$1.11 run 22.09 T1824 · 29 Sep 2026prompt.txt
Fraktur Adverts 99.5±0.2 ≈1of 114 $75$0.37 run 24.26 T1814 · 29 Sep 2026prompt_optimized.txt
General Meeting Minutes 95.3±3.2 ≈1of 108 $54$0.49 run 15.43 T1823 · 29 Sep 2026prompt.txt
Library Cards 91.4±1.2 ≈1of 114 $13$3.46 run 5.98 T1815 · 27 Sep 2026prompt.txt
Magazine Pagesother prompt 96.8±2.8 ≈1of 115 $19$0.87 run 4.29 T1822 · 27 Sep 2026prompt_explicit-json.txt
Medieval Manuscripts 86.9±9.0 ≈1of 114 $29$0.35 run 7.41 T1816 · 29 Sep 2026prompt.txt
Personnel Cards 97.5±0.8 ≈1of 114 $52$3.17 run 12.5 T1821 · 27 Sep 2026prompt.txt

Price

FromInput, $ per million tokensOutput, $ per million tokensSource
27 Sep 20264.020.0archived price page

Every run

  1. T1824Duty Rosters29 Sep 202695.7$1.11
  2. T1823General Meeting Minutes29 Sep 202695.3$0.49
  3. T1822Magazine Pages29 Sep 202696.8$1.11
  4. T1821Personnel Cards29 Sep 202697.2$3.10
  5. T1820Book Advert XML Repair29 Sep 202650.6$2.23
  6. T1819Company Lists29 Sep 202669.8$0.66
  7. T1818Company Lists29 Sep 202671.9$0.68
  8. T1817Blacklist Cards29 Sep 202691.6$0.74
  9. T1816Medieval Manuscripts29 Sep 202686.9$0.35
  10. T1815Library Cards29 Sep 202691.0$5.19
  11. T1814Fraktur Adverts29 Sep 202699.5$0.37
  12. T1813Business Letters29 Sep 2026 · 32 signed letters76.0$1.32
  13. T1812Business Letters29 Sep 2026 · 25 unsigned letters92.0$0.77
  14. T1811Business Letters29 Sep 2026 · all 57 letters75.0$2.08
  15. T1810Bibliographic Data29 Sep 202698.7$0.32
  16. T1824Duty Rosters27 Sep 20261.4$1.29
  17. T1823General Meeting Minutes27 Sep 202623.3$0.59
  18. T1822Magazine Pages27 Sep 202696.8$0.87
  19. T1821Personnel Cards27 Sep 202697.5$3.17
  20. T1820Book Advert XML Repair27 Sep 202667.9$2.22
  21. T1819Company Lists27 Sep 20261.7$1.02
  22. T1818Company Lists27 Sep 202677.7$0.73
  23. T1817Blacklist Cards27 Sep 202695.3$0.72
  24. T1816Medieval Manuscripts27 Sep 202686.8$0.36
  25. T1815Library Cards27 Sep 202691.4$3.46
  26. T1814Fraktur Adverts27 Sep 202699.4$0.60
  27. T1813Business Letters27 Sep 2026 · 32 signed letters74.0$1.25
  28. T1812Business Letters27 Sep 2026 · 25 unsigned letters83.0$0.72
  29. T1811Business Letters27 Sep 2026 · all 57 letters75.0$1.98
  30. T1810Bibliographic Data27 Sep 202647.1$0.37