Benchmark · KnowledgeSettled

Cl Bench

Updated 2026-04-02
Models tested
19
Top score
27.9
GPT-5.4
Median
18.7
min 11.4
Top-5 spread
σ 2.6
Competitive

Best score over time · one chart, every benchmark

CL BENCH17 MODELS · FRONTIER RUNNING MAX0255075100SCORE ↑Apr 25Jul 25Oct 25Jan 26Apr 26RELEASE DATE →benchgecko.ai/benchmark/cl-bench · frontier
Frontier on Cl Bench rose from 17.8 to 27.9 in 11 months · +10.1 points · latest leader GPT-5.4 from OpenAI.
Pink dots = frontier records · 3 totalClick to open model page

What it measures · how it is scored · sources · as of 2026-11-17

  • How it is scored · Scored as a percentage · higher is better · maximum 100
  • Released · 2026-02-03
  • Scores from · Epoch AI Benchmarking Hub (19 scores)

Same category · related evaluations