Claude Sonnet 5.5: benchmark results
Provider: Anthropic. Released 2026-09-28. Access: API.
Aggregate Rating 1912 ± 6, rank #19 of 10800 rated models, from 971 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA Coding Agent Index v2.0 - Terminal-Bench 4.0 | 66.16 | Pass@1 (%) | 100 |
| AA MKA - Output File Type - pdf - Regression WSR | 96.52 | Weighted Satisfaction Rate (%) | 100 |
| AA MKA - Output File Type - spreadsheet - Regression WSR | 97.78 | Weighted Satisfaction Rate (%) | 100 |
| AA MKA - Regression WSR | 96.78 | Weighted Satisfaction Rate (%) | 100 |
| AA MKA - Vertical - Construction - Regression WSR | 98.4 | Weighted Satisfaction Rate (%) | 100 |
| AA MKA - Vertical - Law & Government - Climb WSR | 51.01 | Weighted Satisfaction Rate (%) | 100 |
| AA MKA - Vertical - Science - Regression WSR | 97.52 | Weighted Satisfaction Rate (%) | 100 |
| AA-Briefcase - Presentation Elo | 1725.99 | Elo | 100 |
| Agent Arena - Bash Recovery | 15.04 | Bash Recovery (%) | 100 |
| Android Bench 2.0 - Long-horizon | 40 | Mean task pass rate (%) over 30 tasks | 100 |
| CMDB-1500 (Image) | 92.67 | Accuracy (%), fixed denominator of 300 questions (invalid an | 100 |
| Code2Video-Compass - I2V - TQ | 0.11 | Published TQ Score | 100 |
Interactive version: theaggregate.ai/model?slug=claude-sonnet-5-5 · How It Works · Data refreshed daily, snapshot 2026-11-13.