DrugTargetWorld
Agents interpret cardiac MRI and identify proteins associated with causal effects in 20 simulated biobanks. The verifier checks their conclusions against hidden ground truth.
The October 2026 release reports scores for nine models across 540 episodes. Claude Opus 5 led with 39.98 out of 100, followed by GPT-5.6 Sol.
- Made by
- Stanford University and Brown University
- Released
- September 2026
- Kind
- Genomics and life sciences
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Subject
- Clinical medicine, Biological sciences
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Agents, Vision, Robotics, Biology and medicine
- Strongest model tested
- Claude Opus 5 #11 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 20th, 2026
Claude Opus 5 leads with 40.0 among models released by July 2026 Claude Opus 5 leads with 40.0 among models released by July 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in July 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 14 more
- 1 Claude Opus 5 API api-alias@2026-09-07 40.0
- 2 GPT-5.6 Sol API api-alias@2026-09-05 35.4
- 3 Claude Sonnet 5 API api-alias@2026-09-04 21.3
- 4 Claude Haiku 4.5 API api-alias@2026-09-04 12.9
- 5 gpt-oss-20b GPU 6cee5e81 7.41
- 6
Qwen3-Coder-30B-A3B-Instruct GPU b2cff646 5.90
- 7 GLM-4-32B GPU 077b5c2f 1.46
- 8
Qwen3-8B GPU b968826d 1.31
- 9
Devstral Small 1.1 GPU bd165ab2 0.81
Source: Official DrugTargetWorld leaderboard
- 1 Claude Opus 5 API api-alias@2026-09-07 40.0
- 2 GPT-5.6 Sol API api-alias@2026-09-05 35.4
- 3 Claude Sonnet 5 API api-alias@2026-09-04 21.3
- 4 Claude Haiku 4.5 API api-alias@2026-09-04 12.9
- 5 gpt-oss-20b GPU 6cee5e81 7.41
- 6
Qwen3-Coder-30B-A3B-Instruct GPU b2cff646 5.90
- 7
Qwen3-8B GPU b968826d 1.31
- 8
Devstral Small 1.1 GPU bd165ab2 0.81
Source: Official DrugTargetWorld leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 40.0 | API api-alias@2026-09-07 | Jul 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | 35.4 | API api-alias@2026-09-05 | Jul 2026 | Official leaderboard |
| 3 | Claude Sonnet 5 | 21.3 | API api-alias@2026-09-04 | Jun 2026 | Official leaderboard |
| 4 | Claude Haiku 4.5 | 12.9 | API api-alias@2026-09-04 | Oct 2025 | Official leaderboard |
| 5 | gpt-oss-20b | 7.41 | GPU 6cee5e81 | Aug 2025 | Official leaderboard |
| 6 | | 5.90 | GPU b2cff646 | Jul 2025 | Official leaderboard |
| 7 | GLM-4-32B | 1.46 | GPU 077b5c2f | Official leaderboard | |
| 8 | | 1.31 | GPU b968826d | Apr 2025 | Official leaderboard |
| 9 | | 0.81 | GPU bd165ab2 | Jul 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 5 | 40.0 | API api-alias@2026-09-07 | Jul 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | 35.4 | API api-alias@2026-09-05 | Jul 2026 | Official leaderboard |
| 3 | Claude Sonnet 5 | 21.3 | API api-alias@2026-09-04 | Jun 2026 | Official leaderboard |
| 4 | Claude Haiku 4.5 | 12.9 | API api-alias@2026-09-04 | Oct 2025 | Official leaderboard |
| 5 | gpt-oss-20b | 7.41 | GPU 6cee5e81 | Aug 2025 | Official leaderboard |
| 6 | | 5.90 | GPU b2cff646 | Jul 2025 | Official leaderboard |
| 7 | | 1.31 | GPU b968826d | Apr 2025 | Official leaderboard |
| 8 | | 0.81 | GPU bd165ab2 | Jul 2025 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Target ID, Phenotype and Direction. Each ranks models on one part of the test. Claude Opus 5 leads 2 of them, and GPT-5.6 Sol leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Target ID
8 models we track have a score here.
- 1 GPT-5.6 Sol ↑1 15.8
- 2 Claude Opus 5 ↓1 14.8
- 3 Claude Sonnet 5 10.2
- 4 Claude Haiku 4.5 5.27
- 5
Qwen3-Coder-30B-A3B-Instruct ↑1 3.26
- 6 gpt-oss-20b ↓1 2.94
- 7
Devstral Small 1.1 ↑1 0.75
- 8
Qwen3-8B ↓1 0.70
Phenotype
8 models we track have a score here.
- 1 Claude Opus 5 7.19
- 2 GPT-5.6 Sol 3.16
- 3 Claude Sonnet 5 1.16
- 4 gpt-oss-20b ↑1 0.68
- 5
Qwen3-8B ↑2 0.39
- 6 Claude Haiku 4.5 ↓2 0.21
- 7
Qwen3-Coder-30B-A3B-Instruct ↓1 0.14
- 8
Devstral Small 1.1 0.06
Direction
8 models we track have a score here.
- 1 Claude Opus 5 13.1
- 2 GPT-5.6 Sol 13.0
- 3 Claude Sonnet 5 6.96
- 4 Claude Haiku 4.5 5.91
- 5 gpt-oss-20b 3.43
- 6
Qwen3-Coder-30B-A3B-Instruct 1.94
- 7
Qwen3-8B 0.22
- 8
Devstral Small 1.1 0.00
The best score, 40.0, costs $4.14 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official DrugTargetWorld leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5 | API api-alias@2026-09-07 | 40.0 | $4.14 | ||
| GPT-5.6 Sol | API api-alias@2026-09-05 | 35.4 | $2.02 | ||
| Claude Sonnet 5 | API api-alias@2026-09-04 | 21.3 | $1.47 | ||
| Claude Haiku 4.5 | API api-alias@2026-09-04 | 12.9 | $0.26 | ||
| gpt-oss-20b | GPU 6cee5e81 | 7.41 | $0.07 | ||
| GPU b2cff646 | 5.90 | $0.05 | |||
| GPU b968826d | 1.31 | $0.22 | |||
| GPU bd165ab2 | 0.81 | $0.20 |
The best score, 40.0, costs $4.14 a task
Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.
Source: Official DrugTargetWorld leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Opus 5 | API api-alias@2026-09-07 | 40.0 | $4.14 | ||
| GPT-5.6 Sol | API api-alias@2026-09-05 | 35.4 | $2.02 | ||
| Claude Sonnet 5 | API api-alias@2026-09-04 | 21.3 | $1.47 | ||
| Claude Haiku 4.5 | API api-alias@2026-09-04 | 12.9 | $0.26 | ||
| gpt-oss-20b | GPU 6cee5e81 | 7.41 | $0.07 | ||
| GPU b2cff646 | 5.90 | $0.05 | |||
| GPU b968826d | 1.31 | $0.22 | |||
| GPU bd165ab2 | 0.81 | $0.20 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official DrugTargetWorld leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official DrugTargetWorld leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Biology and chemistry
- GeneBench Pro In use Agents analyze messy simulated genomics and biology datasets to estimate a decision-relevant quantity across 129 problems. Scored automatically against known answers. GPT-5.6 Sol 31.5%
- MedChemBench (OpenAI) In use Models work through 99 medicinal chemistry problems drawn from recent papers and patents. Each task mixes prose with structures, assay tables and plots, then asks for the program’s next decision. GPT-6 Astra 83.8%
- SUPERChem In use Models solve 500 expert-written chemistry reasoning problems, offered in multimodal and text-only forms. Expert solution paths also allow a reasoning path score.
Tencent Hy4 preview 66.4%
- LifeSciBench In use Models complete 750 expert-written life science research tasks, often with attached figures, tables, or sequence files. Graded against expert rubrics as score and pass rate. GPT-Rosalind-6 61.3%
- ProtocolQA Open-Ended In use Models correct errors in published lab protocols using open-ended questions adapted from LAB-Bench ProtocolQA. Scored as pass@1. GPT-6 Cyber 47.2%
- MolecularIQ In use Models answer questions about molecular graphs, such as counting, indexing and constrained generation, and a symbolic checker verifies each answer. gpt-oss-120b 47.5%
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (9 entries).
- Pass Models scored 8 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from July 2026, for Claude Opus 5.
- Note Frontier models None of the top 10 has a score. The strongest tested is Claude Opus 5 (#11).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on drugtargetworld.vercel.app: 8 rows for models we track and 1 other entry at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.