Claude-3.5 Sonnet June: benchmark results
Provider: Anthropic. Access: API.
Aggregate Rating 1548 ± 31, rank #1725 of 10916 rated models, from 8 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AI for Education Pedagogy - Social studies | 74.55 | Accuracy (%) | 43.2 |
| AI for Education Pedagogy - Science | 74.86 | Accuracy (%) | 35 |
| AI for Education Pedagogy - Maths | 71.43 | Accuracy (%) | 34.6 |
| AI for Education Pedagogy - Primary | 77.46 | Accuracy (%) | 34.2 |
| AI for Education Pedagogy | 73.08 | Accuracy (%) | 33.6 |
| AI for Education Pedagogy - Secondary | 70.91 | Accuracy (%) | 29.7 |
| AI for Education SEND | 66.06 | Accuracy (%) | 24.9 |
| AI for Education Pedagogy - Technology | 66.98 | Accuracy (%) | 15.4 |
Interactive version: theaggregate.ai/model?slug=claude-3-5-sonnet-june · How It Works · Data refreshed daily, snapshot 2026-11-08.