Who leads the PhysicianBench benchmark?

GPT-5.5 currently leads PhysicianBench with a score of 46.30 on pass@1.

What is the state-of-the-art score on PhysicianBench?

The state-of-the-art result on PhysicianBench is 46.30 (pass@1), achieved by GPT-5.5.

How many models are tracked on PhysicianBench?

Codesota tracks 2 models on PhysicianBench.

Codesota · Agentic AI · Task agents · PhysicianBenchTasks/Agentic AI/Task agents

Task agents · benchmark dataset · EN

PhysicianBench.

Name: PhysicianBench Benchmark Results
Creator: Codesota
License: https://creativecommons.org/licenses/by/4.0/

Submit a result ↵

§ 01 · Leaderboard

Best published scores.

2 results indexed across 1 metric. Shaded row marks current SOTA; ties broken by submission date.

Primary: pass@1 · higher is better

pass@1· primary

2 rows

#	Model	Org	Submitted	Paper / code	pass@1
01	GPT-5.5API	OpenAI	—	paper	46.30
02	DeepSeek-V4-ProAPI	DeepSeek-AI	—	paper	18.70

Fig 2 · Rows sorted by score within each metric. Shaded row marks SOTA. Dates reflect model or paper release where available, otherwise the date Codesota accessed the source.

§ 06 · Contribute

Have a score that beats
this table?

Submit a checkpoint and a reproduction script. We will run it, publish the score, and — if it takes the top — annotate the step on the progress chart with your name.

Submit a result ↵Read submission guide

What a submission needs

01A public checkpoint or API endpoint
02A reproduction script with frozen commit + seed
03Declared evaluation environment (Python, deps)
04One row per metric declared by this dataset
05A contact so we can follow up on discrepancies

PhysicianBench.

Best published scores.

Neighbouring benchmarks.

Have a score that beatsthis table?

Have a score that beats
this table?