OLMo-2-1124-7B-Instruct — benchmark results

Allen AI's instruct variant of the fully open OLMo 2 7B, post-trained with a Tulu 3-style recipe of SFT, DPO, and RLVR. Provider: Allen AI. Released 2024-11-24. Access: Open.

Unified ELO 1414 ± 11, rank #1159 of 1776 rated models, from 121 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - IFEval72.44Score86.3
EuroEval Portuguese NLU - MultiWikiQA PT73.65Reading comprehension Score (%)77.1
EuroEval German NLU - Germanquad57.65Reading comprehension Score (%)75.5
EuroEval English NLU - SQuAD82.43Reading comprehension Score (%)68.4
EuroEval Finnish NLU - Tydiqa FI64.4Reading comprehension Score (%)64.1
HREF28.49Average HREF Score (%)63.6
EuroEval English NLU - SST-566.47Sentiment classification Score (%)63.5
LA Leaderboard - GalCoLA51.96Accuracy (%)63.2
Open LLM Leaderboard - MATH Level 514.88Score61.8
EuroEval Swedish NLU - Swerec75.97Sentiment classification Score (%)59.8
LA Leaderboard - AQuAS65.96Accuracy (%)57.4
EuroEval Icelandic NLU - NQII47.63Reading comprehension Score (%)55.9

Interactive version: theaggregate.ai/model?slug=olmo-2-1124-7b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.