L3-8B-Stheno-v3.2 — benchmark results

Sao10K's community roleplay and creative-writing fine-tune of Llama 3 8B. Provider: Other. Released 2024-06-05. Access: Open.

Unified ELO 1466 ± 28, rank #927 of 1776 rated models, from 10 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - IFEval68.73Score81.6
Open LLM Leaderboard - GPQA8.05Score67.9
Open LLM Leaderboard - MMLU-Pro30.76Score63.6
Open LLM Leaderboard - BBH32.02Score59.7
Open LLM Leaderboard - MATH Level 59.29Score45.1
UGI - Writing30.44Writing Score38.7
Open LLM Leaderboard - MuSR6.45Score30.8
UGI - Willingness (W/10)3.8W/10 Score27.8
UGI Leaderboard20.56UGI Score12.5
UGI - Natural Intelligence12.61NatInt Score10.7

Interactive version: theaggregate.ai/model?slug=l3-8b-stheno-v3-2 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.