Exact model identity

Claude 3.5 Haiku 20241022 (SCIGYM)

Anthropic · version status: reported

Similar model names are never merged automatically. Evaluation membership and numeric result rows only reference the exact ID scigym-claude-3-5-haiku-20241022.

Evaluation settings

Numeric results

BenchmarkWorkRun / groupMetricValue
SCIGYM SmallMeasuring Scientific Capabilities of Language Models with a Systems Biology Dry Labscigym-small-creator-paper
scigym-2025-small-react-initial-concentration-20step-3repeat
Simulation Trajectory Error (STE)0.6281 SMAPE error
SCIGYM SmallMeasuring Scientific Capabilities of Language Models with a Systems Biology Dry Labscigym-small-creator-paper
scigym-2025-small-react-initial-concentration-20step-3repeat
RMS with modifiers — Precision0.0858 score
SCIGYM SmallMeasuring Scientific Capabilities of Language Models with a Systems Biology Dry Labscigym-small-creator-paper
scigym-2025-small-react-initial-concentration-20step-3repeat
RMS with modifiers — Recall0.0421 score
SCIGYM SmallMeasuring Scientific Capabilities of Language Models with a Systems Biology Dry Labscigym-small-creator-paper
scigym-2025-small-react-initial-concentration-20step-3repeat
RMS with modifiers — F10.053 score
SCIGYM SmallMeasuring Scientific Capabilities of Language Models with a Systems Biology Dry Labscigym-small-creator-paper
scigym-2025-small-react-initial-concentration-20step-3repeat
RMS without modifiers — Precision0.1454 score
SCIGYM SmallMeasuring Scientific Capabilities of Language Models with a Systems Biology Dry Labscigym-small-creator-paper
scigym-2025-small-react-initial-concentration-20step-3repeat
RMS without modifiers — Recall0.0805 score
SCIGYM SmallMeasuring Scientific Capabilities of Language Models with a Systems Biology Dry Labscigym-small-creator-paper
scigym-2025-small-react-initial-concentration-20step-3repeat
RMS without modifiers — F10.0987 score