Hedge-Bench - Competitive Positioning: leaderboard

Metric: Macro dense mean rubric score (out of 4) on the Competitive Positioning task category: each trial scores 0 to 4 by the themes it covers, 4 only with full coverage plus a synthesis that reconciles conflicting evidence, averaged within each task and then over the tasks where the model had a valid run; 102 open-ended financial-analyst research tasks derived from recorded expert analyst discussions, run in the Harbor harness with the Terminus 2 agent over a sandboxed document corpus, eight trials per task, graded by a Gemini-3.1-Pro judge against expert rubric moves with hallucination-supported moves discounted; higher is better. Source: arxiv.org. Saturation forecast: Around 2029. 8 models tracked.

Top models

#ModelScore
1Claude Sonnet 4.61.95
2Claude Opus 4.71.74
3Gemini 3.5 Flash1.65
4GPT-5.51.62
5Claude Opus 4.81.26
6Claude Haiku 4.51.24
7Gemini 3.1 Pro (Preview)0.97
8GPT-5.4 Mini0.8

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