Pallas-0.3 [bfloat16] [rev: 1207a09c7bd4]: benchmark results

Provider: Mihaiii. Access: Open.

Aggregate Rating 1468 ± 37, rank #2906 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - MMLU75.09Accuracy (%) (5-shot)96.5
Open LLM Leaderboard v1 - WinoGrande80.19Accuracy (%) (5-shot)72.8
Open LLM Leaderboard v1 - GSM8K59.74Accuracy (%) (5-shot)71.6
Open LLM Leaderboard v1 - TruthfulQA MC257.32MC2 (%) (0-shot)69.8
Open LLM Leaderboard v1 - ARC Challenge63.57Normalized accuracy (%) (25-shot)63.3
Open LLM Leaderboard v1 - HellaSwag83.36Normalized accuracy (%) (10-shot)58

Interactive version: theaggregate.ai/model?slug=pallas-0-3-bfloat16-rev-1207a09c7bd4 · How It Works · Data refreshed daily, snapshot 2026-11-08.