AceCoder-Qwen2.5-7B-Ins-Rule Benchmark Results

AceCoder-Qwen2.5-7B-Ins-Rule: benchmark results

Provider: Other. Access: Open.

Unified ELO 1538 ± 60, rank #900 of 2656 rated models, from 11 benchmark results.

Benchmark	Score	Metric	Percentile
Open LLM Leaderboard - MATH Level 5	49.92	Score	96.9
Open Portuguese LLM - FaQuAD NLI	82.74	Macro F1 (%)	95.3
Open Portuguese LLM - ASSIN2 RTE	94.04	Macro F1 (%)	94.2
Open LLM Leaderboard - IFEval	74.24	Score	89.3
Open Portuguese LLM - ENEM	74.95	Accuracy (%)	88
Open Portuguese LLM - BLUEX	64.26	Accuracy (%)	84.7
Open Portuguese LLM - OAB Exams	53.53	Accuracy (%)	83.8
Open LLM Leaderboard - MMLU-Pro	43.22	Score	78.2
Open LLM Leaderboard - BBH	54.04	Score	69.1
Open LLM Leaderboard - GPQA	30.12	Score	57.4
Open LLM Leaderboard - MuSR	39.8	Score	40.4

Interactive version: theaggregate.ai/model?slug=acecoder-qwen2-5-7b-ins-rule · How It Works · Data refreshed daily, snapshot 2026-09-19.