Claude Sonnet 5 (Low): benchmark results
Provider: Anthropic. Released 2026-06-30. Access: API.
Aggregate Rating 1704 ± 15, rank #348 of 2170 rated models, from 69 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Conceptual Reasoning Index - Argument Evaluation (LMCA) | 49.65 | Chance-Corrected Score (0-100) | 73.3 |
| AA CritPt | 4.57 | Accuracy (%) | 68.9 |
| AA Humanity's Last Exam | 21.92 | Accuracy (%) | 67.7 |
| AA Long Context Reasoning | 67.33 | Accuracy (%) | 56.6 |
| AA GDP.pdf - Real Estate - Criterion Pass Rate | 63.55 | Criterion Pass Rate (%) | 52.7 |
| CellTrack-Bench - Link F1 | 0.52 | Score (0–1) | 52.4 |
| Conceptual Reasoning Index - Consistency (ACCoRD) | 69.47 | Chance-Corrected Score (0-100) | 51.9 |
| AA SciCode | 50.12 | Accuracy (%) | 51.6 |
| Conceptual Reasoning Index | 54.88 | Chance-Corrected Score (0-100) | 51 |
| AA GDP.pdf - Engineering - Criterion Pass Rate | 52.51 | Criterion Pass Rate (%) | 50.2 |
| CellTrack-Bench - Repair F1 | 0.63 | Score (0–1) | 50 |
| StudentBench - Lesson Planning | 0.03 | Expert tutor pairwise preference, Bradley-Terry score (lesso | 50 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-low · How It Works · Data refreshed daily, snapshot 2026-11-05.