FuseChat-Llama-3.1-8B-Instruct — benchmark results

FuseAI's implicit model-fusion tune of Llama 3.1 8B Instruct, distilling Gemma 2 27B, Mistral Large, Qwen2.5 72B and Llama 3.1 70B via SFT+DPO. Provider: Other. Released 2024-11-20. Access: Open.

Unified ELO 1537 ± 62, rank #657 of 1776 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AlpacaEval 2.065.39LC Win Rate (%)94.6
Open LLM Leaderboard - IFEval72.05Score85.7
Open LLM Leaderboard - MATH Level 524.77Score77.9
Open LLM Leaderboard - GPQA7.38Score62.2
Open LLM Leaderboard - MMLU-Pro30.37Score61.7
Open LLM Leaderboard - BBH30.85Score54.7
Open LLM Leaderboard - MuSR6.15Score29.5

Interactive version: theaggregate.ai/model?slug=fusechat-llama-3-1-8b-instruct · How the rankings work · Data refreshed daily, snapshot 2026-07-22.