All benchmarks

GeneBench-Pro

PaperImplementation

Progress Over Time

Interactive timeline showing model performance evolution on GeneBench-Pro

State-of-the-art frontier
Open
Proprietary

GeneBench-Pro Leaderboard

3 models
ContextCostLicense
1
OpenAI
GPT-5.6 SolNew
OpenAI
—1.1M$5.00 / $30.00
2
OpenAI
GPT-5.6 TerraNew
OpenAI
—1.1M$2.50 / $15.00
3
OpenAI
GPT-5.6 LunaNew
OpenAI
—1.1M$1.00 / $6.00
Notice missing or incorrect data?
About this benchmark

What is GeneBench-Pro?

GeneBench-Pro is a research-level benchmark of 129 multi-stage computational-biology problems spanning genomics, quantitative biology, and translational biomedicine. Each problem gives the agent a messy dataset, brief context, and a target estimand, and requires navigating dependent inferential decision points to reach a verifiable answer.

GeneBench-Pro is a text benchmark evaluating models on reasoning, science, and agents tasks. LLM Stats tracks 3 models on this benchmark, scored on a 0–1 scale. The current average is 0.2, with the leader at 0.3.

Compare leaders on the best AI for reasoning, best AI for science and best AI for agents leaderboards.

Current leaders

GPT-5.6 Sol from OpenAI currently leads the GeneBench-Pro leaderboard with a score of 0.287 across 3 evaluated AI models.

1GPT-5.6 SolOpenAI28.7%
2GPT-5.6 TerraOpenAI23.3%
3GPT-5.6 LunaOpenAI10.8%

FAQ

Common questions about the GeneBench-Pro benchmark and leaderboard.

What is the GeneBench-Pro benchmark?

GeneBench-Pro is a research-level benchmark of 129 multi-stage computational-biology problems spanning genomics, quantitative biology, and translational biomedicine. Each problem gives the agent a messy dataset, brief context, and a target estimand, and requires navigating dependent inferential decision points to reach a verifiable answer.

What is the GeneBench-Pro leaderboard?

The GeneBench-Pro leaderboard ranks 3 AI models based on their performance on this benchmark. Currently, GPT-5.6 Sol by OpenAI leads with a score of 0.287. The average score across all models is 0.209.

What is the highest GeneBench-Pro score?

The highest GeneBench-Pro score is 0.287, achieved by GPT-5.6 Sol from OpenAI.

How many models are evaluated on GeneBench-Pro?

3 models have been evaluated on the GeneBench-Pro benchmark, with 0 verified results and 3 self-reported results.

Where can I find the GeneBench-Pro paper?

The GeneBench-Pro paper is available at https://www.biorxiv.org/content/10.64898/2026.06.29.735386v2. The paper details the methodology, dataset construction, and evaluation criteria.

Where can I find the GeneBench-Pro dataset?

The GeneBench-Pro dataset is available on HuggingFace at https://huggingface.co/datasets/ajh-oai/genebench-pro-public-package.

What categories does GeneBench-Pro cover?

GeneBench-Pro is categorized under reasoning, science, and agents. The benchmark evaluates text models.

What's the difference between GeneBench-Pro and GeneBench?

GeneBench-Pro is a variant of GeneBench. See the GeneBench leaderboard for the broader benchmark and per-model comparison.

Which model offers the best value on GeneBench-Pro?

Among models scoring within 10% of the leader, GPT-5.6 Sol from OpenAI is the cheapest, at $5.00 per million input tokens with a score of 0.287.

How recent are the GeneBench-Pro leaderboard results?

The GeneBench-Pro leaderboard was last updated in July 2026 and currently includes 3 evaluated models.