WizardLM-70B: benchmark results
Provider: Microsoft.
Aggregate Rating 1412 ± 32, rank #5530 of 10916 rated models, from 25 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| BenchBench | 56.21 | Aggregate Score (%) | 58.8 |
| AlpacaEval 2.0 | 17.58 | LC Win Rate (%) | 44.6 |
| Chatbot Arena (Text - Creative Writing) | 1198 | Arena Score | 21.3 |
| T-Eval | 44.2 | Overall Score (%) | 20 |
| Chatbot Arena (Text - Writing, Literature & Language) | 1195 | Arena Score | 18.2 |
| Chatbot Arena (Text - Entertainment, Sports & Media) | 1176 | Arena Score | 18 |
| Chatbot Arena (Text - Multi-Turn) | 1167 | Arena Score | 16.4 |
| Chatbot Arena (Text) | 1185 | Elo | 15.1 |
| Chatbot Arena (Text - Non-English) | 1146 | Arena Score | 14.9 |
| Chatbot Arena (Text - English) | 1213 | Arena Score | 14.8 |
| Chatbot Arena (Text - Life, Physical & Social Science) | 1200 | Arena Score | 14.8 |
| Chatbot Arena (Text - Instruction Following) | 1164 | Arena Score | 14.5 |
Interactive version: theaggregate.ai/model?slug=wizardlm-70b · How It Works · Data refreshed daily, snapshot 2026-11-08.