BankerToolBench - Harness - OpenHands: leaderboard
BankerToolBench - Harness - OpenHands. April2026 primary paper v1,100investment-banking tasks;OpenHands comparison;mean rubric score over three runs;GPT5.2/5.4high reasoning. These are not scores for the October dataset v1.1 update. Full100tasks;source Table4;runtime is not scored. Metric: Mean rubric score (%). Primary published table; source configurations remain distinct.
Metric: Mean rubric score (%). Source: arxiv.org. Saturation forecast: Around June 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.2 (High) | 54.5 | #109 (GPT-5.2) |
| 2 | Claude Opus 4.6 | 53 | #60 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=bankertoolbench-harness-openhands · How It Works · Data refreshed daily, snapshot 2026-10-16.