3DVerifierBench
Harbor adapterDVerifierBench Grounding Generative Verification in 3D ContentShuanglin Li, Jiaying Lin, Shuquan Ye.
- Samples
- 2,581
- Released
- 2026
- Scores
- 10
DRYLAB-Bench
DRYLAB-Bench: Benchmarking the Biosecurity Risk of Agentic LLM Mutation Design
Evaluates high-risk biological mutation design capabilities of LLM agents across 30 hazardous scenarios using empirical wet-lab data for safe verification.
How to run
ltb · drylab-bench
$ npm i -g lettokenburn-cli$ ltb bench info drylab-bench
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
12 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| Grok 4.5 | 0.5 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| Qwen3.8 Max | 0.4 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| DeepSeek V4 Flash | 0.4 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| Gemini 3.6 Flash | 0.4 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| Gemini 3.8 Flash | 0.4 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| GPT-5.6 Luna | 0.3 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| GPT-5.6 Sol | 0.3 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| GPT-5.6-terra | 0.2 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| GPT-6 Astra | 0.1 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| Claude Opus 4.8 | 0.1 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| Claude Opus 5 | 0.1 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
| Claude Fable 5 | 0.0 | N/A | Independent | medium | Oct 9, 2026 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
DRYLAB-Bench tasks LLM agents with 30 genuinely hazardous mutation-design scenarios in a multi-round, tool-augmented environment. It leverages specialized biological design tools to iteratively refine candidate sequences.
Scoring uses the Biosecurity Risk Score (BRS), validated against 187,695 empirical measurements from ProteinGym and ViroGym. Results show frontier models pose substantial threats, with tool augmentation significantly amplifying risk.