gemini-1.5-flash

Google

legacy model Its test configurations are retired, so it is no longer run. The figures are from its best legacy runs, scored as they ran at the time; it is not ranked.

average
41.8
benchmarksof 12
3
seconds per inputmean response time
11.3

By benchmark

BenchmarkScoreThe best legacy 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. Legacy models are not ranked.Per 1,000 docss / inputBest run
Bibliographic Dataolder run 28.6 – –– run 12.48 T0029 · 8 Apr 2025prompt.txt
Business Lettersolder run 41.0 – –– run 5.11 T0015 · 11 Apr 2025prompt.txt
Fraktur Advertsolder run 55.8 – –– run 16.39 T0088 · 9 May 2025prompt_optimized.txt

Not run on: Blacklist Cards, Book Advert XML Repair, Company Lists, Duty Rosters, General Meeting Minutes, Library Cards, Magazine Pages, Medieval Manuscripts, Personnel Cards.

Every run

  1. T0088Fraktur Adverts9 May 2025 · legacy configuration55.8–
  2. T0088Fraktur Adverts7 May 2025 · legacy configuration41.8–
  3. T0049Business Letters11 Apr 2025 · 32 signed letters · legacy configuration40.0–
  4. T0048Business Letters11 Apr 2025 · 25 unsigned letters · legacy configuration38.0–
  5. T0015Business Letters11 Apr 2025 · all 57 letters · legacy configuration41.0–
  6. T0029Bibliographic Data8 Apr 2025 · legacy configuration28.6–
  7. T0015Business Letters1 Apr 2025 · all 57 letters · legacy configuration40.0–
  8. T0015Business Letters5 Mar 2025 · all 57 letters · legacy configuration39.0–