List your company

Laboratory Science Knowledge Evaluation on LAB-Bench 2 821 (Evaluation)

82.3AccuracyClaude Opus 4.6
40.90851.65462.473.146May 7, 2026

Evaluation results

MethodLinks
Claude Opus 4.6Type=Commercial LLMs, Setting=BioMedArena2026.0582.3
SOTASource=[11]2026.0580
Claude Sonnet 4.6Type=Commercial LLMs, Setting=BioMedArena2026.0574.3
Claude Opus 4.5Type=Commercial LLMs, Setting=BioMedArena2026.0573.8
GPT-5.4Type=Commercial LLMs, Setting=BioMedArena2026.0572.1
Claude Sonnet 4.5Type=Commercial LLMs, Setting=BioMedArena2026.0571.5
Gemini 3.1 ProType=Commercial LLMs, Setting=BioMedArena2026.0570.9
Nemotron-3 Super 120BType=Public LLMs, Setting=BioMedArena2026.0562.6
GLM-4.5Type=Public LLMs, Setting=BioMedArena2026.0561.5
Trinity-LargeType=Public LLMs, Setting=BioMedArena2026.0561
Gemini 3 FlashType=Commercial LLMs, Setting=BioMedArena2026.0559.8
INTELLECT-3.1Type=Public LLMs, Setting=BioMedArena2026.0557.9
Qwen3-235BType=Public LLMs, Setting=BioMedArena2026.0557.9
Gemini 3.1 ProType=Commercial LLMs, Setting=Baseline2026.0552.1
Gemini 3 FlashType=Commercial LLMs, Setting=Baseline2026.0551.9
Claude Opus 4.6Type=Commercial LLMs, Setting=Baseline2026.0551.2
Claude Opus 4.5Type=Commercial LLMs, Setting=Baseline2026.0549.8
Claude Sonnet 4.6Type=Commercial LLMs, Setting=Baseline2026.0549.3
GPT-5.4Type=Commercial LLMs, Setting=Baseline2026.0548.5
Claude Sonnet 4.5Type=Commercial LLMs, Setting=Baseline2026.0548.1
GLM-4.5Type=Public LLMs, Setting=Baseline2026.0544.8
Nemotron-3 Super 120BType=Public LLMs, Setting=Baseline2026.0543.6
Trinity-LargeType=Public LLMs, Setting=Baseline2026.0543.5
INTELLECT-3.1Type=Public LLMs, Setting=Baseline2026.0543.5
Qwen3-235BType=Public LLMs, Setting=Baseline2026.0542.5