OLMo-2-0325-32B-Instruct: benchmark results

Provider: Allen AI. Released 2025-03-13. Access: Open.

Aggregate Rating 1478 ± 15, rank #2658 of 10318 rated models, from 312 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Grip on LLMs - Dutch Simplification - Amsterdam45.14SARI (0-100)96.7
Grip on LLMs - Dutch Simplification Average43.71SARI (0-100; mean of two datasets)96.7
EuroEval English NLU - SST-569.75Matthews correlation coefficient (%)95.8
EuroEval Dutch NLU - DBRD92.51Matthews correlation coefficient (%)95
EuroEval Greek NLU - Greek SA80.66Matthews correlation coefficient (%)92.6
EuroEval Serbian NLU - MMS SR49.82Matthews correlation coefficient (%)90.6
Open Portuguese LLM - FaQuAD NLI80.67Macro F1 (%)90.6
EuroEval Norwegian NLU - Norec59.7Matthews correlation coefficient (%)90
Grip on LLMs - Dutch Simplification - INT Duidelijke Taal42.29SARI (0-100)90
Grip on LLMs - HonestCityBench - Average38Appropriate acknowledgement rate (%; mean of five categories90
Grip on LLMs - HonestCityBench - Outdated Information53Appropriate acknowledgement rate (%; LLM judge)90
EuroEval Swedish NLU - Swerec78.94Matthews correlation coefficient (%)89.8

Interactive version: theaggregate.ai/model?slug=olmo-2-0325-32b-instruct · How It Works · Data refreshed daily, snapshot 2026-11-14.