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 1647 ± 27, rank #377 of 1776 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - GPQA26.62Score99.9
Open LLM Leaderboard - BBH57.13Score98.8
Open LLM Leaderboard - MuSR21.42Score97.1
Open LLM Leaderboard - MMLU-Pro48.65Score94.9
UGI Leaderboard49.83UGI Score89.6
Open LLM Leaderboard - MATH Level 537.39Score87.8
UGI - Writing44.62Writing Score85.5
UGI - Natural Intelligence33.69NatInt Score81
Open LLM Leaderboard - IFEval66.81Score78.9
UGI - Willingness (W/10)6.2W/10 Score57.7

Interactive version: theaggregate.ai/model?slug=70b-l3-3-cirrus-x1 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.