GenomeQA
Models answer multiple-choice questions about short genomic sequences. The benchmark covers six task families, including species classification.
- Made by
- Weicai Long and colleagues
- Released
- April 2026
- Kind
- Genomics and life sciences
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Biological sciences
- Language
- English
- In and out
- Text, Molecules and sequences → Text
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Biology and medicine
- Strongest model tested
-
Gemini 3 Pro #56 on the capability index
- Last model added
- November 2025
- Scores refreshed
- November 20th, 2026
Gemini 3 Pro leads with 63.6% among models released by November 2025
Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports accuracy by question format, so the headline averages its binary and multiple-choice scores. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in November 2025, 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 16 more
- 1
Gemini 3 Pro Thinking 63.6%
- 2 GPT-5.1 Thinking 56.5%
- 3 Claude Sonnet 4.5 Thinking 56.3%
- 4 Grok 4.1 Thinking 55%
- 5
Qwen3-Max Thinking 50.9%
- 6
Llama 4 Maverick Non-thinking 49.1%
Source: The GenomeQA paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 63.6% | Thinking | Nov 2025 | Official leaderboard |
| 2 | GPT-5.1 | 56.5% | Thinking | Nov 2025 | Official leaderboard |
| 3 | Claude Sonnet 4.5 | 56.3% | Thinking | Sep 2025 | Official leaderboard |
| 4 | Grok 4.1 | 55% | Thinking | Nov 2025 | Official leaderboard |
| 5 | | 50.9% | Thinking | Sep 2025 | Official leaderboard |
| 6 | | 49.1% | Non-thinking | Apr 2025 | Official leaderboard |
Rankings by part
We read 14 parts from the benchmark’s paper, each ranking models on one part of the test, such as Binary-choice questions, Multiple-choice questions and BCQ: Enhancer and Promoter Identification. Gemini 3 Pro leads 12 of them, and GPT-5.1 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
Binary-choice questions
6 models we track have a score here.
- 1
Gemini 3 Pro 66.3%
- 2 GPT-5.1 60.8%
- 3 Claude Sonnet 4.5 59.7%
- 4 Grok 4.1 59.3%
- 5
Llama 4 Maverick ↑1 56.6%
- 6
Qwen3-Max ↓1 56.5%
Multiple-choice questions
6 models we track have a score here.
- 1
Gemini 3 Pro 60.9%
- 2 Claude Sonnet 4.5 ↑1 52.8%
- 3 GPT-5.1 ↓1 52.3%
- 4 Grok 4.1 50.7%
- 5
Qwen3-Max 45.3%
- 6
Llama 4 Maverick 41.5%
BCQ: Enhancer and Promoter Identification
6 models we track have a score here.
- 1 GPT-5.1 ↑1 70.6%
- 2 Claude Sonnet 4.5 ↑1 69%
- 3
Gemini 3 Pro ↓2 67.8%
- 4 Grok 4.1 67.6%
- 5
Qwen3-Max 60.6%
- 6
Llama 4 Maverick 55.4%
BCQ: Splice Site Identification
6 models we track have a score here.
- 1 GPT-5.1 ↑1 54.4%
- 2 Claude Sonnet 4.5 ↑1 53.2%
- 3
Llama 4 Maverick ↑3 50%
- 4
Gemini 3 Pro ↓3 50%
- 5
Qwen3-Max 49.8%
- 6 Grok 4.1 ↓2 47.6%
BCQ: Taxonomic Classification
6 models we track have a score here.
- 1
Gemini 3 Pro 78.8%
- 2 GPT-5.1 64.6%
- 3 Grok 4.1 ↑1 63.8%
- 4 Claude Sonnet 4.5 ↓1 61.6%
- 5
Qwen3-Max 60.6%
- 6
Llama 4 Maverick 57%
BCQ: Histone Mark Prediction
6 models we track have a score here.
- 1
Gemini 3 Pro 57.2%
- 2 Claude Sonnet 4.5 ↑1 53.8%
- 3 GPT-5.1 ↓1 53.2%
- 4 Grok 4.1 53.2%
- 5
Llama 4 Maverick ↑1 52.6%
- 6
Qwen3-Max ↓1 51.2%
BCQ: TFBS Prediction
6 models we track have a score here.
- 1
Gemini 3 Pro 59.8%
- 2 Claude Sonnet 4.5 ↑1 56.6%
- 3 GPT-5.1 ↓1 55.8%
- 4 Grok 4.1 54.6%
- 5
Qwen3-Max 54%
- 6
Llama 4 Maverick 51.6%
BCQ: TF Motif Prediction
6 models we track have a score here.
- 1
Gemini 3 Pro 84%
- 2
Llama 4 Maverick ↑4 73%
- 3 Grok 4.1 ↑1 69%
- 4 GPT-5.1 ↓2 66%
- 5 Claude Sonnet 4.5 ↓2 64%
- 6
Qwen3-Max ↓1 63%
MCQ: Enhancer and Promoter Identification
6 models we track have a score here.
- 1
Gemini 3 Pro 66%
- 2 GPT-5.1 62.6%
- 3 Claude Sonnet 4.5 59%
- 4 Grok 4.1 56.2%
- 5
Qwen3-Max 43%
- 6
Llama 4 Maverick 36%
MCQ: Splice Site Identification
6 models we track have a score here.
- 1
Gemini 3 Pro 33.4%
- 2 Claude Sonnet 4.5 ↑1 28.4%
- 3 GPT-5.1 ↓1 26.8%
- 4
Llama 4 Maverick ↑2 26%
- 5
Qwen3-Max 25.8%
- 6 Grok 4.1 ↓2 25.8%
MCQ: Taxonomic Classification
6 models we track have a score here.
- 1
Gemini 3 Pro 77%
- 2 Claude Sonnet 4.5 ↑1 64.6%
- 3 Grok 4.1 ↑1 61.2%
- 4 GPT-5.1 ↓2 61%
- 5
Llama 4 Maverick ↑1 56.2%
- 6
Qwen3-Max ↓1 52.8%
MCQ: Histone Mark Prediction
6 models we track have a score here.
- 1
Gemini 3 Pro 37.8%
- 2 GPT-5.1 36.2%
- 3 Claude Sonnet 4.5 35.8%
- 4 Grok 4.1 33.4%
- 5
Qwen3-Max 33.2%
- 6
Llama 4 Maverick 31.6%
MCQ: TFBS Prediction
6 models we track have a score here.
- 1
Gemini 3 Pro 59%
- 2 GPT-5.1 50.2%
- 3 Grok 4.1 ↑1 48.4%
- 4 Claude Sonnet 4.5 ↓1 48%
- 5
Qwen3-Max 45.2%
- 6
Llama 4 Maverick 34.4%
MCQ: TF Motif Prediction
6 models we track have a score here.
- 1
Gemini 3 Pro 92%
- 2 Claude Sonnet 4.5 ↑1 81%
- 3 Grok 4.1 ↑1 79%
- 4 GPT-5.1 ↓2 77%
- 5
Qwen3-Max 72%
- 6
Llama 4 Maverick 65%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The GenomeQA 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 GenomeQA 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 12 months ago, in November 2025, for Gemini 3 Pro. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 6 models we track.
- Warning Newest score The newest came 12 months ago, in November 2025, for Gemini 3 Pro.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3 Pro (#56).
- Pass Headroom The best is 63.6%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 8 rows for models we track 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.