reasoning benchmark
BixBench
BixBench is a benchmark for real-world bioinformatics and computational biology data analysis. It evaluates AI models on multi-step scientific workflows that require code execution, statistical reasoning, and biological domain knowledge to interpret experimental data.
Updated Aug 11, 2026
Models1
Model coverage1
MetricScore
EvidenceB
BixBench Ranking
Higher score ranks better on this benchmark.
| 01 | OP | 80.5% | 100.0% | 1 | C |
BixBench Highlights
The leading models and scores on this benchmark.
What is BixBench?
What BixBench measures and how its scores work.
BixBench is a benchmark for real-world bioinformatics and computational biology data analysis. It evaluates AI models on multi-step scientific workflows that require code execution, statistical reasoning, and biological domain knowledge to interpret experimental data.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- BixBench
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- bixbench|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about BixBench.
Which model scores highest on BixBench?
GPT-5.5 is currently ranked first with 80.5%.
What does BixBench measure?
BixBench is a benchmark for real-world bioinformatics and computational biology data analysis. It evaluates AI models on multi-step scientific workflows that require code execution, statistical reasoning, and biological domain knowledge to interpret experimental data.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
1 model results are currently shown.
Does this benchmark affect the overall score?
No. This benchmark is shown for reference but does not contribute to the overall score.