MAG (Set-of-Mark): leaderboard

Metric: Task success rate (%; functional WebArena checkers, LLM judge for 29 answer tasks) with Set-of-Mark element selection grounding, 174 held-out test tasks on the six self-hosted WebArena sites; the agent sees screenshots, acts and writes a guide sentence at every step, 25-step budget, one run, the MAG harness; higher is better. Source: arxiv.org. Saturation forecast: Around April 2028. 4 models tracked.

Top models

#ModelScore
1GPT-5.5 (Low)35.6
2Gemini 3.5 Flash (Low)34.5
3Claude Sonnet 4.6 (Low)27.6

Interactive version: theaggregate.ai/benchmark?slug=mag-set-of-mark · How It Works · Data refreshed daily, snapshot 2026-09-29.