Atlas

Benchmarks

← All benchmarks

JobBench Main

Professional Work · 2026-04-17

JobBench Main is the 65-task full-difficulty split spanning 35 occupations, 569 weighted rubric chains, and 2,066 binary criteria. Its official score is the unweighted macro-average of each task's normalized passed-rubric weight, with no partial credit within a chain.

Top models (higher is better)

ModelScore
Claude Opus 565.7
Muse Spark 1.364.9
Muse Spark Open61.8
Muse Spark 1.261.6
GLM-5.361.4
Muse Spark 1.154.7
Kimi K354.3
Atria Dawn Preview50.3
Opus 4.848.4
Opus 4.744.5
GLM-5.243.4
GPT-5.538.3
GPT-5.432.2
Gemini 3.5 Flash31.5
Inkling31.1
GPT-5.226.6
Sonnet 4.520.7
Gemini 3.1 Pro Preview15.9
Loading Atlas data…