pplx-embed 9B lifts agent accuracy to 64%, +4.9 over next best on BrowseComp+
tomaarsen · x · 2026-10-08
Retrieval gains carry into agent answers: on BrowseComp+, Perplexity's GPT-OSS-120B agent with the 9B retriever hits 64.0% accuracy, +4.9 points over the next best ColBERT while making fewer searches. Across 72 text retrieval tasks, the 9B reports 81.3 nDCG@10 and the 0.6B 78.0 (equal average of six groups); training excluded associated benchmark datasets, making it fairly clean.
Related event: Perplexity open-sources pplx-embed-v2-late retrieval models(36 posts)→
More from Models
- GLM V4.1 Looks Like the Best Chinese Model on ARC-2, Says TeortaxesTex — teortaxesTex · 2026-10-08
- Models systematically underestimate their own capabilities, even newest ones — repligate · 2026-10-08
- Nace.AI open-sources Drex 1.1, an 8B diffusion-LM decision model with released weights — nischay_twt · 2026-10-08
- Indie chatbot Auro lets users blind-pick between model versions to shape its personality — TheMoonMidas · 2026-10-08
- Claude Haiku 5.5 spotted in Claude Code update, rumored at $0.1/M input tokens — kimmonismus · 2026-10-08
- Haiku 5.5 day: Anthropic's latest small model appears to ship — scaling01 · 2026-10-08