Benchmark Almanac

DrugDiscoveryBench

GPT-6 Astra 68.7% leads since September 2026
Not in model cards

Agents do early-stage drug discovery work, from target identification to lead optimization, in 82 tasks with one checkable answer each. A judge model grades answers against expert rubrics.

A task counts as solved only at a full rubric score, averaged over three runs with a 120 minute timeout. The judge is GPT-5.4. About 25 entries on the board.

Made by
Scale AI
Released
June 2026
Kind
Genomics and life sciences
Level
Expert
Scored
Graded by a model
Answers
Agent task
Tasks
Public, plus a private test set
Strongest model tested
GPT-6 Astra #3 on the capability index
Last model added
October 2026
Scores refreshed
November 12th, 2026
20
Models scored on its own leaderboard

GPT-6 Astra leads with 68.7%

Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.

20 models. Scroll sideways for the rest.

  1. 68.7 GPT-6 Astra
  2. 65.4 Gemini 4 Argon
  3. 63.4 Kimi K3.1 Pro
  4. 62.2 Muse Spark 1.3
  5. 60.6 DeepSeek V4.1 Flash 1017
  6. 56.5 GPT-5.6 Sol
  7. 53.7 Claude Opus 5
  8. 51.6 GPT-5.5
  9. 50.0 Claude Sonnet 5
  10. 50.0 Gemini 3.5 Flash
  11. 46.8 Claude Opus 4.8
  12. 41.9 Gemini 3.1 Pro
  13. 36.2 GLM-5.2
  14. 35.3 Kimi K2.7 Code
  15. 31.7 DeepSeek-V4-Pro
  16. 31.3 Claude Sonnet 4.6
  17. 29.3 GPT-5.2
  18. 29.3 Qwen3.7-Max
  19. 27.7 Claude Opus 4.6
  20. 22.8 MiniMax-M3
  1. 1 GPT-6 Astra max 68.7%
  2. 2 Gemini 4 Argon high 65.4%
  3. 3 Kimi K3.1 Pro xhigh 63.4%
  4. 4 Muse Spark 1.3 high 62.2%
  5. 5 DeepSeek V4.1 Flash 1017 xhigh 60.6%
  6. 6 GPT-5.6 Sol max 56.5%
  7. 7 Claude Opus 5 max 53.7%
  8. 8 GPT-5.5 xhigh 51.6%
  9. 9 Claude Sonnet 5 max 50%
  10. 10 Gemini 3.5 Flash high 50%
  11. 11 Claude Opus 4.8 max 46.8%
  12. 12 Gemini 3.1 Pro high 41.9%
  13. 13 GLM-5.2 xhigh 36.2%
  14. 14 Kimi K2.7 Code xhigh 35.3%
  15. 15 DeepSeek-V4-Pro xhigh 31.7%
  16. 16 Claude Sonnet 4.6 max 31.3%
  17. 17 GPT-5.2 xhigh 29.3%
  18. 18 Qwen3.7-Max xhigh 29.3%
  19. 19 Claude Opus 4.6 max 27.7%
  20. 20 MiniMax-M3 xhigh 22.8%

Source: Official DrugDiscoveryBench leaderboard

#ModelScoreSettingDateSource
1 GPT-6 Astra 68.7% max, mini-SWE-agent Sep 2026 Official leaderboard
2 Gemini 4 Argon 65.4% high, mini-SWE-agent Sep 2026 Official leaderboard
3 Kimi K3.1 Pro 63.4% xhigh, mini-SWE-agent Oct 2026 Official leaderboard
4 Muse Spark 1.3 62.2% high, mini-SWE-agent Sep 2026 Official leaderboard
5 DeepSeek V4.1 Flash 1017 60.6% xhigh, mini-SWE-agent Oct 2026 Official leaderboard
6 GPT-5.6 Sol 56.5% max, Codex Jul 2026 Official leaderboard
7 Claude Opus 5 53.7% max, Claude Code Jul 2026 Official leaderboard
8 GPT-5.5 51.6% xhigh, mini-SWE-agent Apr 2026 Official leaderboard
9 Claude Sonnet 5 50% max, mini-SWE-agent Jun 2026 Official leaderboard
10 Gemini 3.5 Flash 50% high, Gemini CLI May 2026 Official leaderboard
11 Claude Opus 4.8 46.8% max, mini-SWE-agent May 2026 Official leaderboard
12 Gemini 3.1 Pro 41.9% high, Gemini CLI Feb 2026 Official leaderboard
13 GLM-5.2 36.2% xhigh, mini-SWE-agent Jun 2026 Official leaderboard
14 Kimi K2.7 Code 35.3% xhigh, mini-SWE-agent Jun 2026 Official leaderboard
15 DeepSeek-V4-Pro 31.7% xhigh, mini-SWE-agent Apr 2026 Official leaderboard
16 Claude Sonnet 4.6 31.3% max, mini-SWE-agent Feb 2026 Official leaderboard
17 GPT-5.2 29.3% xhigh, Codex Dec 2025 Official leaderboard
18 Qwen3.7-Max 29.3% xhigh, mini-SWE-agent May 2026 Official leaderboard
19 Claude Opus 4.6 27.7% max, Claude Code Feb 2026 Official leaderboard
20 MiniMax-M3 22.8% xhigh, mini-SWE-agent Jun 2026 Official leaderboard

4 models have held number one on the official leaderboard since its release in June 2026

Lab claims count from the day the card came out, independent runs from the model’s release.

OpenAI Meta
Own leaderboard 4 leaders
GPT-6 Astra 68.7%

Source: Official DrugDiscoveryBench leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-6 Astra Muse Spark 1.3 GPT-5.6 Sol GPT-5.5 Gemini 3.1 Pro Claude Sonnet 4.6 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) GPT-6 Astra Muse Spark 1.3

Source: Official DrugDiscoveryBench leaderboard

No lab model card reports it yet

We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.

More in Biology and chemistry

All 108 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%
  • 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%
  • MedChemBench (OpenAI) In use Models answer chemistry questions from an OpenAI internal set, grouped with OpenAI's life science research evaluations. OpenAI has not published the task format. GPT-Rosalind-6 49.6%
  • 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%