MegaBeam-Mistral-7B-300k Benchmark Results

MegaBeam-Mistral-7B-300k: benchmark results

Provider: Other. Released 2024-05-13. Access: Open.

Unified ELO 1373 ± 1, rank #1212 of 1392 rated models, from 15 benchmark results.

Benchmark	Score	Metric	Percentile
Open Chinese LLM - TruthfulQA MC	57.78	Accuracy (%)	74.2
Open LLM Leaderboard - IFEval	52.03	Score	62
Open Korean LLM Leaderboard	37.07	Average Score (%)	57.8
Open LLM Leaderboard - MuSR	8.35	Score	39.6
Open LLM Leaderboard - BBH	19.29	Score	28.8
Open LLM Leaderboard - GPQA	3.13	Score	28.5
Open LLM Leaderboard - MMLU-Pro	17.21	Score	26.2
Open LLM Leaderboard - MATH Level 5	2.11	Score	14.7
Open Chinese LLM - WinoGrande	59.51	Accuracy (%)	11.7
Open Chinese LLM - GSM8K	14.78	Accuracy (%)	11
Open Chinese LLM - ARC Challenge	41.47	Accuracy (%)	8.9
Open Chinese LLM Leaderboard	43.28	Average Score (%)	7.7

Interactive version: theaggregate.ai/model?slug=megabeam-mistral-7b-300k · How It Works · Data refreshed daily, snapshot 2026-09-05.