Perplexity Open-Sources WANDR — 500-Task Benchmark for Wide & Deep Research

On July 14, 2026, Perplexity (@perplexity_ai) open-sourced WANDR — Wide ANd Deep Research — the internal benchmark it built to train and measure Perplexity Computer's wide-and-deep research stack. The release ships 500 tasks, 170,495 required source-backed records, an Apache 2.0 GitHub harness, and a blunt headline number: even Search as Code — Perplexity's best system — hits only 0.133 hard F1 on the full suite.

WANDR is the wide sibling of DRACO (deep long-form reports). Where DRACO asks "write a complete objective report," WANDR asks "find every qualifying company, employee, filing, or competitor — and prove each row with a page that actually says what you claim." explainx.ai maps task shape, grading, leaderboard reality, and why Perplexity published it now.

TL;DR

Wide + deep — the two capabilities Perplexity encodes

From Perplexity's X thread:

"Wide-and-deep research requires two capabilities. (1) Agents must search broadly enough to find all qualifying entities. (2) Agents must investigate deep enough to support every claim with evidence."

Real jobs cited: competitive mapping, due diligence, literature review, market analysis, product comparison, talent sourcing — the work people already delegate to Computer + SaC, not chatbot trivia.

Hierarchical tasks — qualification key trees

WANDR represents requirements as hierarchical, independently verifiable records:

company(n) → employee(m) → url(k)

Example task ceo_cfo_appointments: Find 70 US companies with CEO/CFO appointments (Mar–Apr 2026) · 70 appointment URLs · 70 separate listing-authority URLs → 140 records, shared company key. Missing listing proof = incomplete member even if appointment page is perfect.

That structure is why hard F1 punishes agents harder than soft F1 — one broken branch zeros the whole member.

500 tasks — scale and difficulty

Tasks are seeded from de-identified production patterns — not synthetic Jeopardy prompts. Pipeline stages: seeding → authoring (author–critic loop) → admission (feasibility + judge audit) → curation.

Key insight from Perplexity: Difficulty is not scale alone — it depends on work per record (disambiguation, cross-source checks, regulatory nuance).

Reference-free grading — no stale gold answers

Fixed answer keys fail for open-ended research. WANDR instead:

1. Solve — normalize agent output
2. Fetch — retrieve each cited URL (browser retry on failure)
3. Judge — identity resolution + per-record verdict
4. Score — precision, recall, soft/hard F1 up the hierarchy

Each record: item + URL + excerpts + answer. Grader checks page usability, claim scope, excerpt fidelity, and whether evidence supports every requirement.

Perplexity SaC: 0.531 retrieval-only soft F1 → 0.363 full soft F1. The gap is evidence construction, not search alone.

Leaderboard — SaC leads; nobody wins

Six production systems on all 500 tasks (pinned configs, same verifier):

Perplexity's June SaC article cited ~2.5× over next-best on WANDR — consistent with 0.363 vs ~0.15 class scores for others.

Unsaturated: Best hard precision ~0.150, hard recall ~0.134 — leader earns full credit for roughly one in seven requested members. Perplexity states plainly: "Wide-and-deep research is still a long way from solved."

Effort scaling (45-task subset): Perplexity xhigh reaches 0.447 soft / 0.224 hard F1; cost spans $0.03 (Exa low) to $324.83 (Gemini max) per task.

Four findings that matter for builders

1. Partial progress is common; complete coverage is not

Every system's soft recall sits below soft precision — denominators hurt once full volume counts.

2. Scale compounds failure

Largest volume bins: Perplexity hard precision falls 0.235 → 0.096; recall 0.219 → 0.079.

3. Deeper hierarchies are harsher

Three or more intermediate keys: Perplexity hard precision 0.392 → 0.019.

4. Discovery bottlenecks before judging

Mean top-level discovery completion 0.611–0.951 across systems. Duplicate collapse loses only 0.017–0.205 points — under-delivery, not dedup, dominates.

Page vs excerpt failures: Only 3.2%–8.9% unusable pages (except OpenAI 23.1%). 57.5%–86.6% of excerpts fail to support full claims — the hard part is evidence packaging, not link-finding.

Why open-source now — product + research loop

Ties to July 9 GLM 5.2 orchestrator preview — WANDR is the scoreboard Perplexity used for cost vs Opus math on Computer tasks.

Running WANDR locally — cost warning

From the README:

Requires API keys for solvers (OpenAI, Anthropic, Perplexity, Exa, Parallel, Gemini) and judge/fetch paths. Harbor does not impose a spending cap.

WANDR vs other agent benchmarks

For teams building GEO / competitive intelligence pipelines, see GEO for marketers — WANDR is the eval layer for whether your agent actually covers the full competitor set, not just writes a convincing summary.

Summary

WANDR (July 14, 2026) is Perplexity's open Apache 2.0 benchmark for wide-and-deep research agents: 500 tasks, 170,495 required evidence records, hierarchical qualification trees, and reference-free URL re-fetch grading. Search as Code leads at 0.363 soft F1 and 0.133 hard F1; Anthropic is second; every other tested stack scores lower. Hard F1 near 0.13 means the field — including Perplexity — is nowhere near solved.

For developers, the repo is a runnable spec of what Perplexity Computer optimizes for. For the market, it reframes "research agents" from one beautiful report to 170 thousand verifiable rows — a harder, more honest bar.

Related Reading

• Germany ZAK — Perplexity subject to media law (Jul 2026)
• Perplexity Search as Code — 2.5× on WANDR
• Perplexity Computer GLM 5.2 Orchestrator — WANDR cost math
• Perplexity Brain — Computer memory system
• AI Benchmarks Complete Guide (2026)
• What Are AI Agents?
• GEO for Marketers — AI Answer Engines
• WANDR on GitHub
• Perplexity research article

Scores, task counts, and system comparisons reflect Perplexity's July 14, 2026 release. Re-run benchmarks on pinned configs before citing leaderboard numbers in production decisions.