SkillsBench

SkillsBench - evaluated on the public SkillsBench v1.1 benchmark across 87 tasks, reporting the average score over three runs per task.

Category

General Agents

Max Score

—

Score Type

percent

Active

Yes

Model Scores

Scores for SkillsBench

Model Score Date Verified
Fable-5
93.67%
18.08.2026 Unverified
GPT-5.6 Sol
100.00%
18.08.2026 Unverified
Claude Opus 4.8
79.56%
18.08.2026 Unverified
Qwen3.7-Max
70.07%
18.08.2026 Unverified
Qwen3.8-2.4T-A95B
91.97%
18.08.2026 Verified
Muse-Glimmer-30B
28.95%
01.08.2026 Verified
Gemma4-31B-it
32.40
01.08.2026 Unverified
Qwen3.6-27B
34.55%
01.08.2026 Unverified