blossom-v5.1-9B Benchmark Results

blossom-v5.1-9B — benchmark results

Provider: Other. Released 2024-05-15. Access: Open.

Unified ELO 1275 ± 78, rank #1582 of 1776 rated models, from 14 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - GPQA	11.41	Score	82.7
Open LLM Leaderboard - MMLU-Pro	33.1	Score	73.3
Open LLM Leaderboard - MATH Level 5	21.22	Score	73.1
Open LLM Leaderboard - BBH	34.2	Score	67.6
Open Chinese LLM - TruthfulQA MC	55.63	Accuracy (%)	64.1
Open LLM Leaderboard - IFEval	50.86	Score	60.7
Open LLM Leaderboard - MuSR	8.02	Score	37.6
Open Chinese LLM - WinoGrande	57.14	Accuracy (%)	7.4
Open Chinese LLM - ARC Challenge	36.86	Accuracy (%)	4.5
Open Chinese LLM - HellaSwag	41.78	Accuracy (%)	4.5
Open Chinese LLM Leaderboard	33.34	Average Score (%)	2.1
Open Chinese LLM - GSM8K	0	Accuracy (%)	1.2

Interactive version: theaggregate.ai/model?slug=blossom-v5-1-9b · How the rankings work · Data refreshed daily, snapshot 2026-07-22.