OmicsBench v1
Agents analyze molecular data across eight benchmarks. LatchBio reports pass rates for 741 short tasks and 43 long tasks.
LatchBio operates 21 public biology leaderboards. Its October 19 publication introduces this specific combination of eight task sets.
- Made by
- LatchBio
- Released
- October 2026
- Kind
- Genomics and life sciences
- Level
- Expert
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Biological sciences
- Language
- English
- Interaction
- Agentic
- Environment
- Code sandbox
- Items from
- Another benchmark
- Refresh
- New versions replace it
- Run by
- A host
- In views
- Agents, Biology and medicine
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 21st, 2026
GPT-6 Astra leads with 40.8% among models released by September 2026 GPT-6 Astra leads with 40.8% among models released by September 2026
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of its short-horizon and long-horizon pass rates. Where a model ran with several settings or harnesses, we keep its best. 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 September 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-6.1 Sol
- and 11 more
- 40.8 GPT-6 Astra
- 38.0 GPT-5.6 Sol
- 37.6 Claude Opus 5
- 37.4 GPT-6 Sol
- 35.0 Grok 4.6
- 34.9 Grok 4.7
- 34.5 Claude Opus 4.8
- 34.1 GPT-5.5
- 33.0 DeepSeek V4.1-F
- 31.9 Gemini 3.7-F
- 30.3 Claude Sonnet 5
- 30.0 Gemini 3.8-F
- 29.7 Claude Opus 4.7
- 29.6 Claude Opus 5.5
- 29.2 Kimi K3
- 27.1 GPT-6 Luna
- 26.4 GPT-5.6 Luna
- 24.0 Claude Sonnet 4.6
- 1 GPT-6 Astra 40.8%
- 2 GPT-5.6 Sol 38%
- 3 Claude Opus 5 37.6%
- 4 GPT-6 Sol 37.4%
- 5 Grok 4.6 35%
- 6 Grok 4.7 34.9%
- 7 Claude Opus 4.8 34.5%
- 8 GPT-5.5 34.1%
- 9 DeepSeek V4.1-F 33%
- 10 Gemini 3.7-F 31.9%
- 11 Claude Sonnet 5 30.3%
- 12 Gemini 3.8-F 30%
- 13 Claude Opus 4.7 29.7%
- 14 Claude Opus 5.5 29.6%
- 15 Kimi K3 29.2%
- 16 GPT-6 Luna 27.1%
- 17 GPT-5.6 Luna 26.4%
- 18 Claude Sonnet 4.6 24%
Source: The OmicsBench v1 paper
- 1 GPT-6 Astra 40.8%
- 2 GPT-5.6 Sol 38%
- 3 Claude Opus 5 37.6%
- 4 GPT-6 Sol 37.4%
- 5 Grok 4.6 35%
- 6 Grok 4.7 34.9%
- 7 Claude Opus 4.8 34.5%
- 8 GPT-5.5 34.1%
- 9 Claude Sonnet 5 30.3%
- 10 Claude Opus 4.7 29.7%
- 11 Claude Opus 5.5 29.6%
- 12 Kimi K3 29.2%
- 13 GPT-6 Luna 27.1%
- 14 GPT-5.6 Luna 26.4%
- 15 Claude Sonnet 4.6 24%
Source: The OmicsBench v1 paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 40.8% | Pi | Sep 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | 38% | CX | Jul 2026 | Official leaderboard |
| 3 | Claude Opus 5 | 37.6% | CC | Jul 2026 | Official leaderboard |
| 4 | GPT-6 Sol | 37.4% | Pi | Sep 2026 | Official leaderboard |
| 5 | Grok 4.6 | 35% | Pi | Aug 2026 | Official leaderboard |
| 6 | Grok 4.7 | 34.9% | Pi | Sep 2026 | Official leaderboard |
| 7 | Claude Opus 4.8 | 34.5% | Pi | May 2026 | Official leaderboard |
| 8 | GPT-5.5 | 34.1% | Pi | Apr 2026 | Official leaderboard |
| 9 | DeepSeek V4.1-F | 33% | Pi | Official leaderboard | |
| 10 | Gemini 3.7-F | 31.9% | Pi | Official leaderboard | |
| 11 | Claude Sonnet 5 | 30.3% | Pi | Jun 2026 | Official leaderboard |
| 12 | Gemini 3.8-F | 30% | Pi | Official leaderboard | |
| 13 | Claude Opus 4.7 | 29.7% | CC | Apr 2026 | Official leaderboard |
| 14 | Claude Opus 5.5 | 29.6% | CC | Sep 2026 | Official leaderboard |
| 15 | Kimi K3 | 29.2% | Pi | Jul 2026 | Official leaderboard |
| 16 | GPT-6 Luna | 27.1% | Pi | Sep 2026 | Official leaderboard |
| 17 | GPT-5.6 Luna | 26.4% | Pi | Jul 2026 | Official leaderboard |
| 18 | Claude Sonnet 4.6 | 24% | Pi | Feb 2026 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra | 40.8% | Pi | Sep 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | 38% | CX | Jul 2026 | Official leaderboard |
| 3 | Claude Opus 5 | 37.6% | CC | Jul 2026 | Official leaderboard |
| 4 | GPT-6 Sol | 37.4% | Pi | Sep 2026 | Official leaderboard |
| 5 | Grok 4.6 | 35% | Pi | Aug 2026 | Official leaderboard |
| 6 | Grok 4.7 | 34.9% | Pi | Sep 2026 | Official leaderboard |
| 7 | Claude Opus 4.8 | 34.5% | Pi | May 2026 | Official leaderboard |
| 8 | GPT-5.5 | 34.1% | Pi | Apr 2026 | Official leaderboard |
| 9 | Claude Sonnet 5 | 30.3% | Pi | Jun 2026 | Official leaderboard |
| 10 | Claude Opus 4.7 | 29.7% | CC | Apr 2026 | Official leaderboard |
| 11 | Claude Opus 5.5 | 29.6% | CC | Sep 2026 | Official leaderboard |
| 12 | Kimi K3 | 29.2% | Pi | Jul 2026 | Official leaderboard |
| 13 | GPT-6 Luna | 27.1% | Pi | Sep 2026 | Official leaderboard |
| 14 | GPT-5.6 Luna | 26.4% | Pi | Jul 2026 | Official leaderboard |
| 15 | Claude Sonnet 4.6 | 24% | Pi | Feb 2026 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s paper: Short horizon and Long horizon. Each ranks models on one part of the test. Grok 4.7 leads Short horizon and GPT-5.6 Sol leads Long horizon. Arrows show how far a model moved from its overall rank among the models we track.
Short horizon
15 models we track have a score here.
- 1 Grok 4.7 ↑5 49.4%
- 2 GPT-6 Astra ↓1 49.3%
- 3 Grok 4.6 ↑2 48.8%
- 4 Claude Opus 5 ↓1 47.7%
- 5 GPT-6 Sol ↓1 44.9%
- 6 Claude Opus 4.8 ↑1 44.3%
- 7 GPT-5.6 Sol ↓5 43.3%
- 8 Claude Opus 5.5 ↑3 43%
- 9 GPT-5.5 ↓1 41.6%
- 10 Claude Sonnet 5 ↓1 40.5%
Long horizon
15 models we track have a score here.
- 1 GPT-5.6 Sol ↑1 32.8%
- 2 GPT-6 Astra ↓1 32.3%
- 3 GPT-6 Sol ↑1 29.9%
- 4 Claude Opus 5 ↓1 27.6%
- 5 GPT-5.5 ↑3 26.7%
- 6 Claude Opus 4.8 ↑1 24.7%
- 7 Grok 4.6 ↓2 21.5%
- 8 Grok 4.7 ↓2 20.8%
- 9 Claude Opus 4.7 ↑1 20.3%
- 10 Claude Sonnet 5 ↓1 20.1%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The OmicsBench v1 paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official OmicsBench v1 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 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (18 entries).
- Pass Models scored 15 models we track, plus 3 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for Claude Opus 5.5.
- Note Frontier models Only 2 of the top 10 have a score. The strongest tested is GPT-6 Astra (#4).
- Pass Headroom The best is 40.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on blog.latch.bio: 26 rows for models we track and 3 other entries at the last read.
- Pass Last read November 21st, 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.