Latch Bio

VariantBench: Genetic Variant Discovery and Interpretation

Agentic genetic variant analysis, from raw sequencing data to variant interpretation.

genomicsvariant-analysiscodetabularsequence
Status
curated
Saturation
unknown
Reproduction
not yet
Published results
38 results

Editor's note

Official current V1 results cover 118 evaluation records. Model-and-harness configurations are retained separately.

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 552.8% macro-mean pass rateV1 · Claude Code · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 5.551.7% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 5.551.1% macro-mean pass rateV1 · Claude Code · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 550.6% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 5.550.6% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 5.549.7% macro-mean pass rateV1 · Claude Code · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 5.5*48.9% macro-mean pass rateV1 · Claude Code · LSVP · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 5.5*48.6% macro-mean pass rateV1 · Pi · LSVP · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6 Astra46.6% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6.1 Sol46.1% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Grok 4.745.5% macro-mean pass rateV1 · Grok Build · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6 Astra45.2% macro-mean pass rateV1 · Codex · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6.1 Sol43.2% macro-mean pass rateV1 · Codex · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 4.842.4% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 4.842.4% macro-mean pass rateV1 · Claude Code · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Fable 5.1*40.7% macro-mean pass rateV1 · Claude Code · LSVP · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Grok 4.640.4% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 539.8% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Grok 4.639.0% macro-mean pass rateV1 · Grok Build · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 539.0% macro-mean pass rateV1 · Claude Code · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6 Sol38.7% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.6 Sol35.3% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 4.735.0% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.6 Sol34.2% macro-mean pass rateV1 · Codex · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Opus 4.733.0% macro-mean pass rateV1 · Claude Code · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Gemini 3.7 Flash31.4% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Gemini 3.8 Flash31.4% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Kimi K331.4% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
DeepSeek V4.1 Flash31.1% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 4.631.1% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.530.5% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-6 Luna27.7% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.6 Luna27.1% macro-mean pass rateV1 · Codex · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Claude Sonnet 4.626.3% macro-mean pass rateV1 · Claude Code · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
GPT-5.6 Luna24.0% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Mistral Large 4.0 Preview22.0% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Nemotron 3 Ultra 550B A55B17.8% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07
Nemotron 3.5 Lightning14.4% macro-mean pass rateV1 · Pi · 118 evaluation recordsLatch Bio · V1 leaderboard
2026-10-07

Sources