pythia-410m-sft-full [bfloat16] [rev: 4fd9c56aba82]: benchmark results

Provider: EleutherAI.

Aggregate Rating 1116 ± 35, rank #10567 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K1.29Accuracy (%) (5-shot)16.3
Open LLM Leaderboard v1 - TruthfulQA MC240.11MC2 (%) (0-shot)13
Open LLM Leaderboard v1 - HellaSwag39.92Normalized accuracy (%) (10-shot)8.1
Open LLM Leaderboard v1 - WinoGrande53.67Accuracy (%) (5-shot)8
Open LLM Leaderboard v1 - MMLU25.28Accuracy (%) (5-shot)7.3
Open LLM Leaderboard v1 - ARC Challenge26.11Normalized accuracy (%) (25-shot)5.4

Interactive version: theaggregate.ai/model?slug=pythia-410m-sft-full-bfloat16-rev-4fd9c56aba82 · How It Works · Data refreshed daily, snapshot 2026-11-08.