# FrontierBioML: Evaluating agents on machine learning tasks in computational biology (FrontierBioML)

> Valen Labs' benchmark of AI agents doing machine learning work in computational biology: 25 tasks in antibody development, designed binders, protein engineering, structural biology and functional genomics. Each agent builds a model from experimental data in an offline sandbox, and its prediction script is scored on held-out measurements, from 0 (a simple baseline) to 100 (a perfect answer), over three runs per task.

Canonical page: https://benchlm.ai/benchmarks/frontierbioml

- Category: [Agentic](/agentic)
- Last updated: Valen Labs data of 13 November 2026

## About FrontierBioML

- Year: 2026
- Tasks: 25 machine learning tasks in computational biology across antibodies, designed binders, protein engineering, structural biology and functional genomics
- Format: Offline agent sandbox (4 to 32 CPUs, no GPU, about 6 hours); the submitted prediction script runs twice on held-out data; 3 runs per task, 75 per model
- Difficulty: Building and validating models on messy biological data that generalize to held-out antigens, families, cell types and targets
- Paper: [FrontierBioML: Evaluating agents on machine learning tasks in computational biology](https://valenlabs.com/blog/frontierbioml)

Each task gives the agent real experimental data, sometimes deliberately messy (stale identifiers, contamination, swapped labels), and a written brief: rank antibody variants from sequencing counts, predict nanobody binding to unseen antigen variants, score docking poses, infer gene networks from knock-down screens, forecast cancer gene dependencies, choose a panel of enzyme or binder designs under a budget. The agent works offline in a sandbox with 4 to 32 CPUs, no GPU and about six hours. It submits a prediction script and, on most tasks, a shortlist of candidates. Valen runs the script twice in a separate grading sandbox on held-out data; the two runs must give identical output. Each task's metrics are scaled so that its reference baseline sits at or near 0 and a perfect answer at 100 (the baselines average 13.1). The headline is the mean of per-task mean scores over three runs per task, 75 runs per model. A run blocked by a provider's biosafety filter or failing the grading checks counts as 0. Models run in a harness: Claude models in Claude Code, OpenAI models in Codex CLI, the rest in OpenCode. BenchLM recomputes the score from the run-level data on the FrontierBioML site and keeps each task's mean in its history.

FrontierBioML is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (11 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [Claude Mythos 5.2](/models/claude-mythos-5-2) | max reasoning · Claude Code · $48.17 and 2.5 h per run | Anthropic | 40.3% |
| 2 | [Gemini 4 Carbon](/models/gemini-4-carbon) | high reasoning · OpenCode · $8.52 (estimated) and 1.8 h per run | Google | 39.0% |
| 3 | [Gemini 4 Argon](/models/gemini-4-argon) | high reasoning · OpenCode · 1 of 75 runs not graded · $6.71 and 1.6 h per run | Google | 36.8% |
| 4 | [Claude Opus 5.5](/models/claude-opus-5-5) | max reasoning · Claude Code · $12.58 and 1.2 h per run | Anthropic | 36.5% |
| 5 | [GPT-6.1 Sol](/models/gpt-6-1-sol) | max reasoning · Codex CLI · 17 of 75 runs blocked by a biosafety filter · $1.96 and 26 min per run | OpenAI | 29.1% |
| 6 | [GPT-6 Astra](/models/gpt-6-astra) | max reasoning · Codex CLI (Azure) · 19 of 75 runs blocked by a biosafety filter · $10.30 and 33 min per run | OpenAI | 28.8% |
| 7 | [Muse Wonder](/models/muse-wonder) | max reasoning · OpenCode · $6.38 and 34 min per run | Meta | 26.9% |
| 8 | [Kimi K3.1 Pro](/models/kimi-3-1-pro) | max reasoning · OpenCode · 4 of 75 runs not graded · $2.29 and 34 min per run | Moonshot AI | 25.8% |
| 9 | [Grok 4.7](/models/grok-4-7) | xhigh reasoning · OpenCode · 1 of 75 runs not graded · $5.04 and 39 min per run | xAI | 24.0% |
| 10 | [DeepSeek V4.1 Flash 1017](/models/deepseek-v4-1-flash) | max reasoning · OpenCode · 5 of 75 runs not graded · $0.21 and 1.5 h per run | DeepSeek | 22.4% |
| 11 | [Nemotron 3.5 Super VL 120B A12B](/models/nemotron-3-5-super-vl-120b-a12b) | on reasoning · OpenCode (PrimeIntellect) · 13 of 75 runs not graded · $0.11 and 12 min per run | NVIDIA | 11.0% |

## FAQ

### What does FrontierBioML measure?

Whether an AI agent can do machine learning work in computational biology: build a model from experimental data on antibodies, proteins, structures or gene screens, and produce predictions or a shortlist of candidates that hold up on held-out measurements. Each of 25 tasks is scored from 0 (a simple baseline) to 100 (a perfect answer).

### Which model leads FrontierBioML?

Claude Mythos 5.2 in Claude Code leads at 40.3, followed by Gemini 4 Carbon at 39.0, Gemini 4 Argon at 36.8 and Claude Opus 5.5 at 36.5 (Valen Labs data of November 13, 2026).

### Why do the GPT-6 models score lower on FrontierBioML?

OpenAI's biology filter blocked 17 of GPT-6.1 Sol's 75 runs and 19 of GPT-6 Astra's, and blocked runs count as 0. Valen was not verified for OpenAI's life-science access program, while the Claude models ran under Anthropic's Life Science Verification Program.