Llama 3 70B Fireplace Benchmark Results

Llama 3 70B Fireplace — benchmark results

Valiant Labs' function-calling fine-tune of Llama 3 70B Instruct trained on the glaive-function-calling-v2 dataset. Provider: Meta. Released 2024-05-09. Access: Open.

Unified ELO 1476 ± 28, rank #886 of 1776 rated models, from 14 benchmark results.

Strongest benchmark results

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - IFEval	77.74	Score	93.8
Open Chinese LLM - CMMLU	71.6	Accuracy (%)	92
Open LLM Leaderboard - BBH	49.56	Score	90.7
Open LLM Leaderboard - GPQA	13.98	Score	89.4
Open LLM Leaderboard - MMLU-Pro	43.25	Score	87
Open LLM Leaderboard - MuSR	16.77	Score	86.8
Open Chinese LLM - C-Eval Semantic	85.71	Accuracy (%)	77.4
Open LLM Leaderboard - MATH Level 5	21.45	Score	73.5
Open Chinese LLM Leaderboard	59.99	Average Score (%)	70.3
Open Chinese LLM - ARC Challenge	51.79	Accuracy (%)	47.3
Open Chinese LLM - GSM8K	39.95	Accuracy (%)	39.5
Open Chinese LLM - TruthfulQA MC	52.19	Accuracy (%)	35.3

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