J.O.S.I.E.3-Beta10-7B-slerp [bfloat16] [rev: f6673f42a708]: benchmark results

Provider: Other.

Aggregate Rating 1417 ± 33, rank #5311 of 10916 rated models, from 6 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - GSM8K61.03Accuracy (%) (5-shot)73.4
Open LLM Leaderboard v1 - WinoGrande79.64Accuracy (%) (5-shot)70.3
Open LLM Leaderboard v1 - TruthfulQA MC256.88MC2 (%) (0-shot)69
Open LLM Leaderboard v1 - ARC Challenge63.48Normalized accuracy (%) (25-shot)62.9
Open LLM Leaderboard v1 - HellaSwag83.79Normalized accuracy (%) (10-shot)61.5
Open LLM Leaderboard v1 - MMLU62.88Accuracy (%) (5-shot)57.2

Interactive version: theaggregate.ai/model?slug=j-o-s-i-e-3-beta10-7b-slerp-bfloat16-rev-f6673f42a708 · How It Works · Data refreshed daily, snapshot 2026-11-08.