HarnessOpt-Bench - BrowseComp-Plus: leaderboard

Metric: Normalized gain ((held-out score minus seed score) / (1 minus seed score); negative when the nominated harness is worse than the seed; mean over the contestant's optimization rounds, each held-out case scored three times; BrowseComp-Plus deep-research question answering with a deepseek-v4-flash target agent; seed held-out score 0.462, 66 test cases; the optimizer edits the seed harness under fixed development and validation evaluation budgets and never sees the test partition). Source: arxiv.org. Saturation forecast: Around March 2027. 10 models tracked.

Top models

#ModelScore
1Claude Opus 50.48
2Kimi K30.16
3Claude Sonnet 50.15
4GPT-5.6 Sol0.09
5GPT-5.6 Terra0.02

Interactive version: theaggregate.ai/benchmark?slug=harnessopt-bench-browsecomp-plus · How It Works · Data refreshed daily, snapshot 2026-09-29.