EpiCurveBench - High Reasoning with Code Execution: leaderboard
EpiCurveBench (2026) epidemic curve digitization on all 1,000 charts, scored by EpiCurveSimilarity, an alignment metric that tolerates small time shifts and normalizes value errors by the axis range, with general-purpose models at high reasoning effort and a Python code-execution tool for zooming and cropping. Scale 0 to 100; higher is better.
Metric: EpiCurveSimilarity, ECS (%): edit distance with real penalty between each extracted and ground-truth series (gap penalty 1, value differences normalized by the y-axis range and counted fully above 1%), scaled to 0-100 and averaged over matched series per chart (0 for a missed series), then over the 1,000 real-world epidemic curve images; the model returns the chart data as a TSV from one generic extraction prompt; at high reasoning effort with a Python code-execution tool for zooming and cropping image regions; higher is better. Source: arxiv.org. Saturation forecast: Around August 2027. 4 models tracked. Updated 7 Oct 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | Gemini 2.5 Pro | High | 48 | #276 |
| 2 | GPT-5.2 | High | 44.8 | #185 |
| 3 | Claude Opus 4.5 | High | 40.5 | #160 |
| 4 | Qwen 3 VL 235B A22B Instruct | 29.5 | #532 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=epicurvebench-high-reasoning-with-code-execution · How It Works · Data refreshed daily, snapshot 2026-11-21.