Llama-160M-Chat-v1: benchmark results

Provider: Meta. Access: Open.

Unified ELO 1207 ± 20, rank #2890 of 2928 rated models, from 12 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open LLM Leaderboard v1 - TruthfulQA MC244.16MC2 (%) (0-shot)26.2
Open LLM Leaderboard - MuSR36.61Score21.6
Open LLM Leaderboard v1 - MMLU26.14Accuracy (%) (5-shot)11.5
Open LLM Leaderboard - GPQA25.76Score9.7
Open LLM Leaderboard v1 - HellaSwag35.32Normalized accuracy (%) (10-shot)7.1
Open LLM Leaderboard - IFEval15.75Score6.1
Open LLM Leaderboard - BBH30.36Score6
Open LLM Leaderboard v1 - WinoGrande51.3Accuracy (%) (5-shot)5.4
Open LLM Leaderboard - MMLU-Pro11.36Score5.3
Open LLM Leaderboard - MATH Level 50.6Score5
Open LLM Leaderboard v1 - GSM8K0Accuracy (%) (5-shot)4.6
Open LLM Leaderboard v1 - ARC Challenge24.74Normalized accuracy (%) (25-shot)4.1

Interactive version: theaggregate.ai/model?slug=llama-160m-chat-v1 · How It Works · Data refreshed daily, snapshot 2026-09-23.