OLMo-3 7B Think: benchmark results
Provider: Allen AI. Released 2025-11-20. Access: Open.
Aggregate Rating 1456 ± 31, rank #3516 of 10916 rated models, from 13 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI for Education Pedagogy - Science | 74.86 | Accuracy (%) | 35 |
| AI for Education Pedagogy - Technology | 73.58 | Accuracy (%) | 28.7 |
| AI for Education Pedagogy | 66.41 | Accuracy (%) | 21.7 |
| AI for Education Pedagogy - Secondary | 65.25 | Accuracy (%) | 21.7 |
| AI for Education Pedagogy - Maths | 61.9 | Accuracy (%) | 20.9 |
| AI for Education Pedagogy - Primary | 69.01 | Accuracy (%) | 20.7 |
| AI for Education SEND | 63.3 | Accuracy (%) | 18.1 |
| AI for Education Pedagogy - Social studies | 60 | Accuracy (%) | 18 |
| Wolfram LLM Benchmarking Project | 19.7 | Correct Functionality (%) | 14.9 |
| SLR-Bench - Hard | 0 | Accuracy (%) | 6.4 |
| SLR-Bench - Easy | 15 | Accuracy (%) | 5.5 |
| SLR-Bench - Medium | 1 | Accuracy (%) | 5.5 |
Interactive version: theaggregate.ai/model?slug=olmo-3-7b-think · How It Works · Data refreshed daily, snapshot 2026-11-08.