NUWA Evaluation dossier
LABBench2
Evaluates biology-research tasks to study AI assistance with scientific work rather than only factual recall.
Task and measurement
Benchmark protocol profile
- Task / subject
- Model or agent system under the original task configuration
- Measurement target
- Evaluates biology-research tasks to study AI assistance with scientific work rather than only factual recall.
- Interpretation boundary
- Legitimate biology proficiency is enabling evidence and does not directly establish hazardous end-to-end task ability.
Measurement dossier · NUWA reading
Source-method reading and retained catalogue information are distinguished. Publication does not establish independent evidence or bilingual editorial review.
- Measurement construct
- Can scientific capability tests better approximate useful research work than multiple-choice knowledge questions?
- Task population
- LABBench2 contains over 1,900 tasks across research-support skills, comparing models with and without tools in more realistic contexts.
- Scoring and failure modes
- Research-support task accuracy, with base-model and tool-augmented conditions reported separately.
- System conditions
- More than 1,900 tasks; practical research is still simplified.
- Statistical meaning
- Source-reported result statements; this does not establish trial counts, denominators or an estimator: The authors report model-specific subtask accuracy differences of −26% to −46% relative to the earlier benchmark. Tool augmentation helps variably rather than uniformly (§3).
- Validity and interpretation
- Wet-lab execution, ambiguous goals and days-long iteration remain simplified; verifier reliability and biological breadth are limited (§4.3).
- Appropriate research use
- Model recommendation: use version- and tool-specific results; do not infer operational biological uplift from these scores.
- LABBench2 An Improved Benchmark for AI Systems Performing Biology Research · AbstractSelected original resource https://arxiv.org/html/2604.09554; sha256:333fb7f67888029041cb7ff7df47ada35844806b30ea09197b5258442e65aa72; archived source capture; exact capture time not independently established
- LABBench2 An Improved Benchmark for AI Systems Performing Biology Research · §3 ResultsSelected original resource https://arxiv.org/html/2604.09554; sha256:333fb7f67888029041cb7ff7df47ada35844806b30ea09197b5258442e65aa72; archived source capture; exact capture time not independently established
- LABBench2 An Improved Benchmark for AI Systems Performing Biology Research · §4.3 Limitations and future workSelected original resource https://arxiv.org/html/2604.09554; sha256:333fb7f67888029041cb7ff7df47ada35844806b30ea09197b5258442e65aa72; archived source capture; exact capture time not independently established
Original source charts and materials
Related research questions
References
- [1] Jon M Laurent, Albert Bou, et al.. LABBench2: An Improved Benchmark for AI Systems Performing Biology Research. 2026-02-04. v2 [arXiv]; Author affiliations on the original paper title page; Figure 2