Llama-3-Nanda-10B-Chat — benchmark results

Provider: Meta. Released 2024-10-22. Access: Open.

Unified ELO 1385 ± 38, rank #1291 of 1776 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard - MuSR12.88Score70.7
Open LLM Leaderboard - GPQA6.82Score57.4
Open LLM Leaderboard - BBH29.6Score50.2
Open LLM Leaderboard - MMLU-Pro23.96Score42.4
Open LLM Leaderboard - MATH Level 55.59Score30.9
Open LLM Leaderboard - IFEval29.53Score26.8
HindiGen31.733C3H Score (%)20.6

Interactive version: theaggregate.ai/model?slug=llama-3-nanda-10b-chat · How the rankings work · Data refreshed daily, snapshot 2026-07-22.