Tripo AI 3D Generator
Mini toolsGeneBench-Pro
GeneBench-Pro: Evaluating Multistage Statistical Reasoning in Genomics, Quantitative Biology, and Translational Biomedicine
A 129-problem benchmark testing whether AI agents can perform realistic, multi-stage scientific analyses in genomics, quantitative biology, and translational biomedicine. Each problem gives a messy, synthetically-generated dataset with known ground truth and requires the agent to navigate ambiguous judgment calls, choose the correct analysis path, and arrive at a graded numerical answer. Best model (GPT-5.6 Sol) scores 28.7% (31.5% in Pro mode) as of release.
Agentic
Text
Accuracy
Max 100.0%
Released Jun 2026
1
Results
1
Models scored
28.7%
Top: GPT 5.6 Sol (max)
28.7%
Median
Best results
Top primary scores; one row per model.
Frontier over time
Each dot is one model result; the line traces the running best score.
Not enough data to plot a trend yet.
All results
Showing one canonical row per model. Show all configurations
| # | Model | Score | Conditions | Eval date | Source | Flags |
|---|---|---|---|---|---|---|
| 1 | GPT 5.6 Sol (max) | 28.7% | agentic | 30 Jun 2026 | Self-reported | Primary |
