OLMo-7B-hf Benchmark Results

OLMo-7B-hf: benchmark results

Provider: Allen AI. Access: Open.

Unified ELO 1272 ± 22, rank #2773 of 2928 rated models, from 12 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard v1 - HellaSwag	77.31	Normalized accuracy (%) (10-shot)	30.5
Open LLM Leaderboard - GPQA	27.27	Score	27.6
Open LLM Leaderboard - IFEval	27.19	Score	24.2
Open LLM Leaderboard v1 - WinoGrande	69.38	Accuracy (%) (5-shot)	23.4
Open LLM Leaderboard v1 - GSM8K	3.79	Accuracy (%) (5-shot)	22
Open LLM Leaderboard v1 - ARC Challenge	45.65	Normalized accuracy (%) (25-shot)	21
Open LLM Leaderboard v1 - MMLU	28.13	Accuracy (%) (5-shot)	15.7
Open LLM Leaderboard - BBH	32.79	Score	15.2
Open LLM Leaderboard - MuSR	34.87	Score	12
Open LLM Leaderboard - MATH Level 5	1.21	Score	8.7
Open LLM Leaderboard - MMLU-Pro	11.73	Score	8.6
Open LLM Leaderboard v1 - TruthfulQA MC2	35.93	MC2 (%) (0-shot)	2.9

Interactive version: theaggregate.ai/model?slug=olmo-7b-hf · How It Works · Data refreshed daily, snapshot 2026-09-23.