ABRA - Hard: leaderboard
Metric: Hard-tier score (longitudinal new-lesion localisation, end-to-end BI-RADS reporting from breast MRI), composite 0.2 Planning + 0.3 Execution + 0.5 Outcome, each normalised to 0-1, times 100; the agent operates an OHIF viewer and an Orthanc DICOM server through 21 tools, temperature 0, provider-default reasoning effort, single run; tasks that hit the turn cap without submitting score Outcome 0; higher is better. Source: arxiv.org. Saturation forecast: Not forecast. 10 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K2.5 | 46 |
| 2 | Mistral Large 3 | 45 |
| 3 | Gemini 3.1 Pro (Preview) | 44 |
| 4 | Claude Sonnet 4.6 | 44 |
| 5 | GPT-5.4 Nano | 42 |
| 6 | Ministral 3 14B | 41 |
| 7 | GPT-5.4 (2026-03-05) | 40 |
| 8 | Gemini 3 Flash (Preview) | 36 |
Interactive version: theaggregate.ai/benchmark?slug=abra-hard · How It Works · Data refreshed daily, snapshot 2026-10-07.