Open LLM Leaderboard - IFEval Leaderboard

Open LLM Leaderboard - IFEval: leaderboard

Metric: Score. Source: huggingface.co. 4576 models tracked.

#	Model	Score
1	Llama 3.3 70B Instruct	89.98
2	Llama 3.1 70B Instruct	86.69
3	Qwen 2.5 72B Instruct	86.38
4	Rombos-LLM-V2.6-Qwen-14B	84.32
5	Qwen2.5-14B-Instruct-1M	84.14
6	Mistral Large 2 (Nov) Instruct (2411)	84.01
7	Qwen 2.5 32B Instruct	83.46
8	Qwen2.5-32B-Instruct-abliterated-v2	83.34
9	zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES	83.28
10	Qwen2.5-14B-Instruct-abliterated-v2	83.28
11	Configurable-Llama-3.1-8B-Instruct	83.12
12	Llama-3.1-Tulu-3-70B-DPO	82.82
13	Llama-3.1-Tulu-3-8B	82.67
14	Awqward2.5-32B-Instruct	82.55
15	lambda-qwen2.5-14B-dpo-test	82.31

Interactive version: theaggregate.ai/benchmark?slug=open-llm-leaderboard-ifeval · How It Works · Data refreshed daily, snapshot 2026-09-05.