All benchmarks

MedChemBench (Internal)

Paper

Progress Over Time

Interactive timeline showing model performance evolution on MedChemBench (Internal)

State-of-the-art frontier
Open
Proprietary

MedChemBench (Internal) 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 MedChemBench (Internal)?

MedChemBench is an internal OpenAI evaluation of medicinal-chemistry reasoning, testing whether models can support drug-discovery-relevant chemistry analysis and decision-making.

MedChemBench (Internal) is a text benchmark evaluating models on reasoning, science, and healthcare tasks. LLM Stats tracks 3 models on this benchmark, scored on a 0–1 scale. The current average is 0.4, with the leader at 0.5.

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

Current leaders

GPT-5.6 Sol from OpenAI currently leads the MedChemBench (Internal) leaderboard with a score of 0.483 across 3 evaluated AI models.

1GPT-5.6 SolOpenAI48.3%
2GPT-5.6 TerraOpenAI35.0%
3GPT-5.6 LunaOpenAI30.4%

FAQ

Common questions about the MedChemBench (Internal) benchmark and leaderboard.

What is the MedChemBench (Internal) benchmark?

MedChemBench is an internal OpenAI evaluation of medicinal-chemistry reasoning, testing whether models can support drug-discovery-relevant chemistry analysis and decision-making.

What is the MedChemBench (Internal) leaderboard?

The MedChemBench (Internal) leaderboard ranks 3 AI models based on their performance on this benchmark. Currently, GPT-5.6 Sol by OpenAI leads with a score of 0.483. The average score across all models is 0.379.

What is the highest MedChemBench (Internal) score?

The highest MedChemBench (Internal) score is 0.483, achieved by GPT-5.6 Sol from OpenAI.

How many models are evaluated on MedChemBench (Internal)?

3 models have been evaluated on the MedChemBench (Internal) benchmark, with 0 verified results and 3 self-reported results.

Where can I find the MedChemBench (Internal) paper?

The MedChemBench (Internal) paper is available at https://openai.com/index/gpt-5-6/. The paper details the methodology, dataset construction, and evaluation criteria.

What categories does MedChemBench (Internal) cover?

MedChemBench (Internal) is categorized under reasoning, science, and healthcare. The benchmark evaluates text models.

Which model offers the best value on MedChemBench (Internal)?

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 0.483.

How recent are the MedChemBench (Internal) leaderboard results?

The MedChemBench (Internal) leaderboard was last updated in July 2026 and currently includes 3 evaluated models.