Latch Bio
MetagenomicsBench: Microbial Community Analysis
Analysis of microbial communities, host–microbiome associations, microbial function and longitudinal dynamics.
metagenomicsmicrobiomecodetabular
Status
curated
Saturation
unknown
Reproduction
not yet
Published results
34 results
Editor's note
Official current V1 results cover 100 evaluation records. Unreported model scores are omitted, not counted as failures.
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.
| Model | Score | Variant | Source |
|---|---|---|---|
| Claude Opus 5.5* | 62.7% macro-mean pass rate | V1 · Claude Code · LSVP · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Opus 5.5* | 62.3% macro-mean pass rate | V1 · Pi · LSVP · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Fable 5.1* | 61.7% macro-mean pass rate | V1 · Claude Code · LSVP · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Sonnet 5.5 | 60.0% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Sonnet 5.5 | 60.0% macro-mean pass rate | V1 · Claude Code · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Opus 5 | 54.0% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Opus 5 | 53.3% macro-mean pass rate | V1 · Claude Code · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Opus 4.8 | 50.0% macro-mean pass rate | V1 · Claude Code · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| GPT-6 Astra | 49.7% macro-mean pass rate | V1 · Codex · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Grok 4.7 | 48.7% macro-mean pass rate | V1 · Grok Build · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Opus 4.8 | 48.3% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| GPT-6 Astra | 47.0% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Opus 5.5 | 43.7% macro-mean pass rate | V1 · Claude Code · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Sonnet 5 | 42.3% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| GPT-6 Sol | 42.0% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Grok 4.6 | 42.0% macro-mean pass rate | V1 · Grok Build · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Sonnet 5 | 41.0% macro-mean pass rate | V1 · Claude Code · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Opus 5.5 | 39.3% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Grok 4.6 | 38.7% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| DeepSeek V4.1 Flash | 38.0% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Opus 4.7 | 35.3% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Gemini 3.7 Flash | 31.7% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| GPT-5.6 Sol | 31.3% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| GPT-6 Luna | 30.7% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| GPT-5.6 Sol | 28.7% macro-mean pass rate | V1 · Codex · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Sonnet 4.6 | 28.3% macro-mean pass rate | V1 · Claude Code · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Claude Sonnet 4.6 | 27.7% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Kimi K3 | 27.3% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Gemini 3.8 Flash | 26.7% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| GPT-5.6 Luna | 24.3% macro-mean pass rate | V1 · Codex · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| GPT-5.6 Luna | 22.7% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Mistral Large 4.0 Preview | 20.0% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Nemotron 3 Ultra 550B A55B | 16.3% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |
| Nemotron 3.5 Lightning | 7.7% macro-mean pass rate | V1 · Pi · 100 evaluation records | Latch Bio · V1 leaderboard 2026-10-07 |