T3Q-Llama3-8B-Inst-sft1.0: benchmark results

Provider: Other. Access: Open.

Aggregate Rating 1458 ± 43, rank #3532 of 10552 rated models, from 9 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Korean LLM - Ko-IFEval47.56Strict accuracy, prompt/instruction mean (%)92
Open Korean LLM - Ko-GSM8K (flexible extract)50.49Exact match, flexible extract (%)84.1
Open Korean LLM - Ko-EQ-Bench31.04EQ-Bench score80.1
Open Korean LLM - Ko-GPQA-Diamond25.25Normalized accuracy (%)75.9
Open Korean LLM - KorNAT-Helpful48.7Normalized accuracy (%)71.5
Open Korean LLM Leaderboard39.01Average Score (%)69.2
Open Korean LLM - KorNAT-CKA25.78Normalized accuracy (%)60.7
Open Korean LLM - Ko-Winogrande58.48Accuracy (%)39.2
Open Korean LLM - KorNAT-Harmless61.64Normalized accuracy (%)32.1

Interactive version: theaggregate.ai/model?slug=t3q-llama3-8b-inst-sft1-0 · How It Works · Data refreshed daily, snapshot 2026-11-16.