Perplexity open-sources WANDR benchmark to evaluate deep research agents
The framework is built on the Harbor platform using real production traces.
Combined views
201.1K
12 Sources, first seen ago
Sources
SU 
Suhail@SuhailPerplexity is very good at building these benchmarks. Whenever I study them in-depth, it’s always the strongest in the field. DRACO was excellent compared to all the other Deep Research ones, for instance. https://twitter.com/perplexity_ai/status/2077099503723946121
- likes: 137
- replies: 13
- bookmarks: 104
- reposts: 9
AK Andy Konwinski@andykonwinskithe companies that figure out how to capture their value propositions into evals and envs will win. the ability to create high quality evaluations is a new type of strategic advantage, and it is more important than access to capital, economies of scale, network effects, or any…
- likes: 34
- replies: 3
- bookmarks: 8
- reposts: 6
SU Suhail@SuhailThe Perplexity is very good at building these benchmarks. Whenever I study them in-depth, it’s always the strongest in the field. DRACO was excellent compared to all the other Deep Research ones, for instance. https://twitter.com/perplexity_ai/status/2077099503723946121
- likes: 7
- replies: 2
- bookmarks: 4
- reposts: 0
AS Aravind Srinivas@AravSrinivasPerplexity has the best (both on cost and performance) deep and wide research harness in Computer. One of the contributing factors is strong internal evals and benchmarks. Today, we're open-sourcing WANDR, the benchmark we use internally for measuring research capabilities.…
- likes: 529
- replies: 31
- bookmarks: 120
- reposts: 47
B( Beff (e/acc)@beffjezosW I D E research is the way https://twitter.com/perplexitydevs/status/2077157305855205629
- likes: 90
- replies: 1
- bookmarks: 20
- reposts: 5
AS Aravind Srinivas@AravSrinivasWide Research is now available in Perplexity Agent API https://twitter.com/perplexitydevs/status/2077157305855205629
- likes: 272
- replies: 20
- bookmarks: 72
- reposts: 26