VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

IFEval (HF Open LLM)

23 models tracked

IFEval (strict, prompt+instance) from the HF Open LLM Leaderboard v2. Baseline 0 → values are already raw accuracy. No same-model overlap with standard ifeval to validate integration → unpooled.

#ModelVendorBest scoreRunsLast seen
1Qwen 14B B100Alibaba77.612026-07-04
2Yi 1.5 34B Chat01.AI60.712026-07-04
3Yi 1.5 9B Chat01.AI60.512026-07-04
4Qwen2.5 7B Test NovelistAlibaba53.512026-07-04
5Yi 1.5 6B Chat01.AI51.512026-07-04
6Yi Coder 9B Chat01.AI48.212026-07-04
7Marco-o1AIDC-AI47.712026-07-04
8Yi 1.5 34B Chat 16K01.AI45.612026-07-04
9Qwen2.5 1.5B Continuous LearntAlibaba45.112026-07-04
10Yi 1.5 9B Chat 16K01.AI42.112026-07-04
11smartllama3.1-8B-001Meta35.212026-07-04
12Yi 1.5 34B 32K01.AI31.212026-07-04
13Yi 1.5 9B01.AI29.412026-07-04
14Yi 1.5 34B01.AI28.412026-07-04
15NuminaMath-7B-TIRAI-MO27.612026-07-04
16Llama Squared 8BMeta27.612026-07-04
17Yi 9B01.AI27.112026-07-04
18NuminaMath-7B-CoTAI-MO26.912026-07-04
19Yi 1.5 6B01.AI26.212026-07-04
20Llama 3 Instruct 8BMeta2412026-07-04
21Yi 9B 200K01.AI23.312026-07-04
22Yi 1.5 9B 32K01.AI2312026-07-04
23Llama 3.1 8B SquarerootMeta22.112026-07-04

Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.