OLMo 2 7B — benchmark results

Provider: Allen AI. Released 2024-11-01. Access: Open.

Unified ELO 990 ± 94, rank #1773 of 1776 rated models, from 22 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA Humanity's Last Exam5.51Accuracy (%)40.6
Artificial Analysis Intelligence Index3.85Intelligence Index10.5
AA-LCR0Score (self-reported)8.9
AA Long Context Reasoning0Accuracy (%)6.8
AA IFBench24.42Accuracy (%)6.7
AA GPQA Diamond28.79Accuracy (%)5.7
AI for Education Pedagogy - Technology47.17Accuracy (%)5.7
AA Terminal-Bench Hard0Accuracy (%)5.5
AI for Education SEND46.33Accuracy (%)4.7
AI for Education Pedagogy - Science33.33Accuracy (%)4.3
AA SciCode3.7Accuracy (%)4.1
AI for Education Pedagogy36.48Accuracy (%)4.1

Interactive version: theaggregate.ai/model?slug=olmo-2-7b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.