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

BBH (HF Open LLM)

23 models tracked

BBH from the HF Open LLM Leaderboard v2 — its own NORMALIZED scale (per-subtask baselines, not invertible from the aggregate; verified). A separate measurement series by design. Unpooled.

#ModelVendorBest scoreRunsLast seen
1Qwen 14B B100Alibaba49.812026-07-04
2Yi 1.5 34B Chat 16K01.AI44.512026-07-04
3Yi 1.5 34B Chat01.AI44.312026-07-04
4Yi 1.5 34B 32K01.AI43.412026-07-04
5Yi 1.5 34B01.AI42.712026-07-04
6Yi 1.5 9B Chat01.AI3712026-07-04
7Marco-o1AIDC-AI34.812026-07-04
8Yi 1.5 9B Chat 16K01.AI31.512026-07-04
9Yi 1.5 9B01.AI30.512026-07-04
10Qwen2.5 7B Test NovelistAlibaba30.412026-07-04
11Yi 1.5 9B 32K01.AI28.912026-07-04
12Yi 9B01.AI27.612026-07-04
13Yi 9B 200K01.AI26.512026-07-04
14Yi Coder 9B Chat01.AI25.912026-07-04
15smartllama3.1-8B-001Meta24.912026-07-04
16Yi 1.5 6B Chat01.AI23.712026-07-04
17Yi 1.5 6B01.AI2212026-07-04
18Llama Squared 8BMeta21.312026-07-04
19Qwen2.5 1.5B Continuous LearntAlibaba19.812026-07-04
20NuminaMath-7B-CoTAI-MO19.212026-07-04
21Llama 3 Instruct 8BMeta18.412026-07-04
22NuminaMath-7B-TIRAI-MO16.912026-07-04
23Llama 3.1 8B SquarerootMeta8.612026-07-04

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