University of Basel RISE · Research and Infrastructure SupportHumanities Data Benchmark

mistral-large-2512

Mistral
average±3.5 (95%)
49.0
leaderboard rankof 114
≈103
benchmarksof 12
12
per 1,000 documentsmean over its benchmarks
$2.22
seconds per inputmean response time
26.1
Compare with other models Its row in the Matrix All its test runs

By task

  • Data correction

    32.1

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

  • Document understanding

    46.7

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

  • Information extraction

    52.7

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

  • Transcription

    63.6

    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 89.7±13.0 ≈74of 115 $4.10$0.020 run 21.76 T0532 · 4 Jun 2026prompt.txt
Blacklist Cards 33.8±14.7 ≈112of 114 $0.65$0.021 run 7.57 T0539 · 4 Jun 2026prompt.txt
Book Advert XML Repair 11.2±5.2 ≈89of 119 $1.47$0.073 run 13.22 T0542 · 25 Jan 2026prompt.txt
Business Letters 47.0±7.1 ≈104of 114 $2.30$0.13 run 6.32 T0533 · 4 Jun 2026prompt.txt
Company Listsother prompt 33.7±17.2 ≈105of 114 $1.87$0.028 run 17.35 T0541 · 4 Jun 2026prompt_min.txt
Duty Rosters 68.8±2.7 ≈78of 107 $4.76$0.10 run 109.3 T1289 · 24 Jul 2026prompt.txt
Fraktur Adverts 80.2±14.9 ≈32of 114 $4.22$0.021 run 40.89 T0536 · 4 Jun 2026prompt_optimized.txt
General Meeting Minutes 77.6±11.3 ≈25of 108 $2.78$0.025 run 17.69 T1239 · 3 Jul 2026prompt.txt
Library Cards 17.9±4.1 113of 114 $0.28$0.072 run 7.01 T0537 · 4 Jun 2026prompt.txt
Magazine Pages 18.1±10.3 ≈66of 115 $0.96$0.044 run 6.29 T0807 · 4 Jun 2026prompt.txt
Medieval Manuscripts 57.4±17.8 ≈72of 114 $1.81$0.014 run 54.67 T0538 · 4 Jun 2026prompt.txt
Personnel Cards 53.1±14.2 ≈106of 114 $1.43$0.087 run 11.62 T0600 · 4 Jun 2026prompt.txt

Price

FromInput, $ per million tokensOutput, $ per million tokensSource
23 Jan 20260.51.5archived price page

Every run

  1. T1289Duty Rosters16 Sep 202661.7$0.099
  2. T1239General Meeting Minutes16 Sep 202676.4$0.025
  3. T1289Duty Rosters24 Jul 202668.8$0.10
  4. T1239General Meeting Minutes3 Jul 202677.6$0.025
  5. T0807Magazine Pages4 Jun 202618.1$0.044
  6. T0600Personnel Cards4 Jun 202653.1$0.087
  7. T0542Book Advert XML Repair4 Jun 20267.0$0.045
  8. T0541Company Lists4 Jun 202633.7$0.028
  9. T0540Company Lists4 Jun 202628.9$0.016
  10. T0539Blacklist Cards4 Jun 202633.8$0.021
  11. T0538Medieval Manuscripts4 Jun 202657.4$0.014
  12. T0537Library Cards4 Jun 202617.9$0.072
  13. T0536Fraktur Adverts4 Jun 202680.2$0.021
  14. T0535Business Letters4 Jun 2026 · 32 signed letters54.0$0.021
  15. T0534Business Letters4 Jun 2026 · 25 unsigned letters43.0$0.047
  16. T0533Business Letters4 Jun 2026 · all 57 letters47.0$0.13
  17. T0532Bibliographic Data4 Jun 202689.7$0.020
  18. T0807Magazine Pages23 Mar 20262.1$0.028
  19. T0538Medieval Manuscripts18 Feb 20260.0$0.005
  20. T0535Business Letters18 Feb 2026 · 32 signed letters0.0$0.011
  21. T0534Business Letters17 Feb 2026 · 25 unsigned letters0.0$0.009
  22. T0533Business Letters17 Feb 2026 · all 57 letters0.0$0.020
  23. T0600Personnel Cards9 Feb 202617.6$0.38
  24. T0542Book Advert XML Repair25 Jan 202611.2$0.073
  25. T0541Company Lists25 Jan 20260.0$0.011
  26. T0540Company Lists25 Jan 20260.4$0.019
  27. T0539Blacklist Cards24 Jan 202615.8$0.012
  28. T0537Library Cards24 Jan 20260.0$0.19
  29. T0536Fraktur Adverts24 Jan 20260.0$0.002
  30. T0532Bibliographic Data24 Jan 20266.7$0.007