Benchmark Almanac

Apertus 1.5 70B

Apertus 1.5 70B.

Swiss AI Initiative Released July 24th, 2026 Family Apertus The lab's model card Compare with others
4
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Swiss AI Initiative Jul 2026

Apertus 1.5 70B

Open weights Flagship

No Epoch Capabilities Index score yet
  • CulturalRiddles 19.6% #9 /20
  • LEXam-hard 24.4% #12 /15

Where it ranks

Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.

Knowledge and language

BenchmarkScoreRankSource
CulturalRiddles 19.6% #9 of 20 Official leaderboard
SEA-HELM 55.2 #56 of 71 Official leaderboard
Last Translation Benchmark 0.66 #36 of 36 Official leaderboard

Professional work

BenchmarkScoreRankSource
LEXam-hard 24.4% #12 of 15 Official leaderboard