Mercury: benchmark results
Provider: Inception. Access: API.
Aggregate Rating 1506 ± 43, rank #2253 of 10916 rated models, from 20 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SnakeBench | 31.9 | TrueSkill Rating | 90.5 |
| Chatbot Arena (Text - Business, Management & Financial Ops) | 1322 | Arena Score | 40.8 |
| Chatbot Arena (Text - Software & IT Services) | 1353 | Arena Score | 39.3 |
| Chatbot Arena (Text - Coding) | 1364 | Arena Score | 39 |
| Chatbot Arena (Text - Life, Physical & Social Science) | 1335 | Arena Score | 37.7 |
| TopoBench (Easy) | 7 | Accuracy (proportion of puzzles solved, times 100; the mean | 37.5 |
| Chatbot Arena (Text - Hard Prompts (English)) | 1336 | Arena Score | 36.5 |
| Chatbot Arena (Text - Multi-Turn) | 1299 | Arena Score | 35.2 |
| Chatbot Arena (Text - Hard Prompts) | 1318 | Arena Score | 34.5 |
| Chatbot Arena (Text - Non-English) | 1286 | Arena Score | 34 |
| Chatbot Arena (Text) | 1306 | Elo | 32.9 |
| Chatbot Arena (Text - English) | 1321 | Arena Score | 32.3 |
Interactive version: theaggregate.ai/model?slug=mercury · How It Works · Data refreshed daily, snapshot 2026-11-08.