Latch Bio

EpiBench: Epigenomics Analysis

Agentic analysis of epigenomics data, including DNA packaging and chemical marks regulating gene activity.

epigenomicscodetabular
Status
curated
Saturation
unknown
Reproduction
not yet
Published results
38 results

Editor's note

Official current V1 results cover 106 evaluation records. Scores are macro-mean pass rates, not whole-study replication rates.

Published results

V1 · current official leaderboard

Current V1 (formerly labeled V2) uses updated evaluation sets and scoring; separate from legacy V0 and paper results. A macro-mean is not a solved-task count. Starred models use Anthropic's LSVP and remain distinct from standard configurations.

ModelScoreVariantSource
Claude Opus 5.5*39.6% macro-mean pass rateV1 · Claude Code · LSVP · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 5.539.0% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 5.538.7% macro-mean pass rateV1 · Claude Code · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 5.5*37.4% macro-mean pass rateV1 · Pi · LSVP · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Fable 5.1*31.8% macro-mean pass rateV1 · Claude Code · LSVP · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 5.530.2% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 5.528.9% macro-mean pass rateV1 · Claude Code · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6 Astra28.3% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6.1 Sol28.3% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.528.3% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 4.825.8% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.6 Sol25.8% macro-mean pass rateV1 · Codex · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
DeepSeek V4.1 Flash25.5% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 525.2% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6.1 Sol24.8% macro-mean pass rateV1 · Codex · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6 Astra24.2% macro-mean pass rateV1 · Codex · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Grok 4.623.6% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 4.722.6% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6 Sol22.0% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Gemini 3.7 Flash22.0% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 521.7% macro-mean pass rateV1 · Claude Code · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.6 Sol21.4% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Gemini 3.8 Flash21.4% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Grok 4.621.1% macro-mean pass rateV1 · Grok Build · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 520.8% macro-mean pass rateV1 · Claude Code · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Grok 4.720.8% macro-mean pass rateV1 · Grok Build · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 4.820.4% macro-mean pass rateV1 · Claude Code · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.6 Luna19.8% macro-mean pass rateV1 · Codex · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 519.5% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6 Luna19.2% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 4.718.9% macro-mean pass rateV1 · Claude Code · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.6 Luna18.9% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 4.618.9% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 4.617.3% macro-mean pass rateV1 · Claude Code · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Kimi K315.7% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Mistral Large 4.0 Preview15.1% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Nemotron 3 Ultra 550B A55B11.3% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Nemotron 3.5 Lightning6.9% macro-mean pass rateV1 · Pi · 106 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07

Sources