70B-L3.3-Cirrus-x1: benchmark results
Sao10K's community creative-writing fine-tune of Llama 3.3 70B. Provider: Other. Released 2025-01-06. Access: Open.
Unified ELO 1636 ± 1, rank #162 of 1392 rated models, from 10 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Open LLM Leaderboard - GPQA | 26.62 | Score | 99.9 |
| Open LLM Leaderboard - BBH | 57.13 | Score | 98.8 |
| Open LLM Leaderboard - MuSR | 21.42 | Score | 97.1 |
| Open LLM Leaderboard - MMLU-Pro | 48.65 | Score | 94.9 |
| UGI Leaderboard | 49.83 | UGI Score | 89.5 |
| Open LLM Leaderboard - MATH Level 5 | 37.39 | Score | 87.8 |
| UGI - Writing | 44.62 | Writing Score | 84.9 |
| UGI - Natural Intelligence | 33.69 | NatInt Score | 80.2 |
| Open LLM Leaderboard - IFEval | 66.81 | Score | 78.9 |
| UGI - Willingness (W/10) | 6.2 | W/10 Score | 58.2 |
Interactive version: theaggregate.ai/model?slug=70b-l3-3-cirrus-x1 · How It Works · Data refreshed daily, snapshot 2026-09-05.