janus-7B Benchmark Results

janus-7B — benchmark results

Provider: KAIST. Released 2024-04-04. Access: Open.

Unified ELO 1361 ± 16, rank #1376 of 1776 rated models, from 14 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MuSR	14.28	Score	78.1
Open Chinese LLM - TruthfulQA MC	53.25	Accuracy (%)	46.9
Open LLM Leaderboard - BBH	25.75	Score	39.7
Open LLM Leaderboard - IFEval	37.75	Score	36.8
Open LLM Leaderboard - MMLU-Pro	20.82	Score	32.7
Open LLM Leaderboard - GPQA	3.02	Score	27.6
Open Chinese LLM - GSM8K	31.46	Accuracy (%)	25.1
Open LLM Leaderboard - MATH Level 5	4.08	Score	23.5
Open Chinese LLM - ARC Challenge	46.16	Accuracy (%)	20.5
Open Chinese LLM - HellaSwag	54.27	Accuracy (%)	20.2
Open Chinese LLM Leaderboard	49.48	Average Score (%)	18.4
Open Chinese LLM - WinoGrande	60.38	Accuracy (%)	16.3

Interactive version: theaggregate.ai/model?slug=janus-7b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.