Atlas

Benchmarks

Synthetic Sciences FrontierML (15 public tasks)

The 15 released tasks of Synthetic Sciences' FrontierML (seven model, five method and three judgment tasks), with the same 12-hour Lab0 runs, Horizon harness and 0-1 normalization as the 25-task headline: the mean over these tasks of one run's normalized score, clipped to 0-1. Grok 4.7 ran only these tasks. It is a component of the Synthetic Sciences FrontierML factor group. Unrelated to Induction Labs' FrontierML (frontierml).

Models
5
Top score
0.6
Leader
Claude Fable 5.2
Updated
Nov 18, 2026
Resolution
—
Saturation
—

No signal or difficulty estimate. Too few models have been measured on this benchmark to estimate its difficulty.

Organizations
5 dated models · 3 frontier modelsClosed weightsOpen weights
Data: Synthetic Sciencesatlas.village.dev

Synthetic Sciences FrontierML (15 public tasks) leaderboard

#ModelSettingScoreSource
1Claude Fable 5.2max · Horizon 0.4.17 (Synthetic Sciences' FrontierML build of mini-swe-agent, under Harbor)
0.6
2Claude Opus 5.5max · Horizon 0.4.17 (Synthetic Sciences' FrontierML build of mini-swe-agent, under Harbor)
0.4
3Gemini 4 Carbonhigh · Horizon 0.4.17 (Synthetic Sciences' FrontierML build of mini-swe-agent, under Harbor)
0.3
4GPT-6 Astramax · Horizon 0.4.17 (Synthetic Sciences' FrontierML build of mini-swe-agent, under Harbor)
0.3
5Grok 4.7x-high · Horizon 0.4.17 (Synthetic Sciences' FrontierML build of mini-swe-agent, under Harbor)
0.1

Related benchmarks

Loading Atlas data…