multimodal benchmark
LifeSciBench Leaderboard
LifeSciBench is an expert-authored and expert-reviewed multimodal benchmark of 750 open-ended life-science research tasks across seven workflows and seven biological domains.
Updated Sep 5, 2026
Models4
Model coverage4
MetricScore
EvidenceB
LifeSciBench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelOP | Score60.30% | Percentile100.00% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelOP | Score59.90% | Percentile66.67% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score56.00% | Percentile33.33% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score51.20% | Percentile0.00% | Participants4 | EvidenceC | Evaluated |
LifeSciBench Highlights
The leading models and scores on this benchmark.
LifeSciBench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for LifeSciBench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is LifeSciBench?
What LifeSciBench measures and how its scores work.
LifeSciBench evaluates responses to open-ended life-science research tasks, many of which require interpreting attached figures, PDFs, and sequence files, using 19,020 physician- and scientist-written rubric criteria.
It measures performance using Score, reported as a ratio, based on grading responses against the rubric criteria rather than multiple-choice answers.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- LifeSciBench
- Modality
- multimodal
- Primary category
- multimodal
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about LifeSciBench.
Which model scores highest on LifeSciBench?
GPT-6 Astra is currently ranked first with 60.30%.
What are the top three models on LifeSciBench?
The current leaders are GPT-6 Astra (60.30%), GPT-5.6 Sol (59.90%), and GPT-5.6 Terra (56.00%).
Which LifeSciBench model has the lowest official input price?
GPT-5.6 Luna has the lowest matched official input price at $0.20 input / $1.2 output per 1M tokens.
Which models are fastest among LifeSciBench results?
The fastest matched records are GPT-5.6 Terra (99.35 tok/s via OpenAI), GPT-5.6 Luna (41.87 tok/s via OpenAI), and GPT-6 Astra (30.66 tok/s via OpenAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.