Search API Benchmark Released: Perplexity Tops the Performance Charts
ArtificialAnlys · x · 2026-08-29
Artificial Analysis has released the Search Index, benchmarking 18 Search API products from 8 providers.
Key Findings:
- Perplexity Search variants (low/medium/high context) occupy the top positions on the leaderboard.
- Cost vs. Performance: Perplexity Search (medium) extends the Pareto frontier, reaching an Index score of 80 at $0.091 per task.
- Context Impact: Increasing search context size reduces the number of searches per task (from 18.0 to 11.4) and lowers total cost, with quality plateauing between medium and high context.
Resources:
- Leaderboard
- Methodology
- Open-source Agent Harness Stirrup
Benchmarks cover DeepSearchQA, BrowseComp, and AA-Omniscience.
Related event: Perplexity Search API Sweeps Top Three in Artificial Analysis Search Index(6 posts)→
More from coding & agent
- Are the fastest GPU kernels now written by AI? Kernels are hyper-verifiable, argues one dev — fleetwood___ · 2026-10-16
- Anthropic lead engineer's 4-question prompt makes agents more ambitious, now a free skill — daniel_mac8 · 2026-10-16
- ChainForge dev shows 'feature map' for orchestrating subagents on large PRs — IanArawjo · 2026-10-16
- aiDotEngineer benchmarks agent orchestration pipelines, staging humans as Foreman and workers — vikvang1 · 2026-10-16
- Developer mass-produces 200 videos in hours using Claude Code + Hyperframes — mcraddock · 2026-10-16
- Penny University hosts software factory discussion; dev shares $40/mo vendor-agnostic AI stack — JnBrymn · 2026-10-16