Atlas

Benchmarks

← All benchmarks

DAYJOB: Data Science

Professional Work

Surge AI's DAYJOB: Data Science extends the DAYJOB suite of long-horizon professional assignments to data science work: each task is a request as brief as a colleague's message plus a workspace of the files it refers to, and an agent judge applies an expert-written rubric to the delivered work. An attempt passes only when it meets at least 95% of the rubric criteria, and the headline is pass@1 at that threshold, as on Surge's DAYJOB: Tax board. Surge runs the benchmark and supplied its first results to Fireworks' Specialized Intelligence Index before publishing the tasks, their number, the harness or the attempt count; the DAYJOB family's published harness is the OpenHands SDK in Harbor with no browsing or package downloads.

Top models (higher is better)

ModelScore
Claude Opus 5.537.3
Claude Sonnet 5.535.3
Claude Fable 5.126.0
Gemini 4 Argon23.3
GPT-6 Astra21.3
GPT-6.1 Sol18.7
Muse Wonder16.7
Grok 4.76.7
Muse Spark 1.36.0
GLM-5.34.0
DeepSeek V4.1 Flash 10173.3
Kimi K31.3
Mistral Large 4 Preview0.7
Loading Atlas data…