openbenchmarks
/

perplexity-low

Model card Files Files and versions

Perplexity (search_context_size=low)

Stub model card so this search API can appear on the OB News Websearch Official Benchmark leaderboard. There are no weights here.

Band: Web search
Endpoint: POST /search
Config: search_context_size=low
Docs: https://docs.perplexity.ai/api-reference/search-post
Live board: https://www.perplexity.ai

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Evaluation results

openbenchmarks/OB-News-Websearch
Accuracy View evaluation results

source

POST /search · search_context_size=low; $ / 1k correct=$5.14; private held-out 300; extract gpt-5.6-terra medium; judge claude-opus-5 Bedrock
97.3 ^*
Web Search View evaluation results

source

POST /search · search_context_size=low; $ / 1k correct=$5.14; private held-out 300; extract gpt-5.6-terra medium; judge claude-opus-5 Bedrock
97.3 ^*
Ar At 1 View evaluation results

source

POST /search · search_context_size=low; $ / 1k correct=$5.14; private held-out 300; extract gpt-5.6-terra medium; judge claude-opus-5 Bedrock
91.7 ^*