AceCoder-Qwen2.5-Coder-7B-Base-Rule Benchmark Results

AceCoder-Qwen2.5-Coder-7B-Base-Rule: benchmark results

Provider: Other. Access: Open.

Unified ELO 1402 ± 61, rank #1892 of 2656 rated models, from 11 benchmark results.

Benchmark	Score	Metric	Percentile
Open Portuguese LLM - ASSIN2 RTE	92.19	Macro F1 (%)	75.7
Open Portuguese LLM - BLUEX	58.41	Accuracy (%)	73.2
Open LLM Leaderboard - MATH Level 5	20.17	Score	71.1
Open Portuguese LLM - OAB Exams	47.74	Accuracy (%)	67.3
Open LLM Leaderboard - MMLU-Pro	37.45	Score	62.3
Open LLM Leaderboard - IFEval	44.08	Score	47.6
Open LLM Leaderboard - BBH	49.02	Score	44.6
Open Portuguese LLM - FaQuAD NLI	53.78	Macro F1 (%)	36
Open Portuguese LLM - ENEM	41.29	Accuracy (%)	30.4
Open LLM Leaderboard - GPQA	27.18	Score	26.7
Open LLM Leaderboard - MuSR	34.49	Score	10.7