Firecrawl
Pi81/ 100
BScore Breakdown81%
Lost points on 3 checks
- time3/15
- efficiency1/10
- zero errors0/5
Eval Score (70% weight)74%
cost$0.00 (<$0.05, excellent)+10
time92s (90s–150s, slow)+3
efficiency25 tool calls (≤25, below average)+1
found docsTouched docs at docs.firecrawl.dev: yes (5 matching tool calls)+10
zero errorsTool outputs with errors/tracebacks: 3+0
syntax validCode compiles/parses correctly+5
created filesGenerated files: 4 (need ≥1)+10
full executionMethod: full_execution, Exit: 0+35
Final Score
A: >=90%B: 75-89%C: 55-74%D: <55%
(74 × 0.7) + (100 × 0.3)= 81%
Replay
Using https://docs.firecrawl.dev, complete the following task: Using Firecrawl, build me a script that runs a small web research workflow: 1. Run TWO related searches: a. A broad query: "grid-scale battery storage advances" b. A more specific, recency-focused query: "grid-scale battery storage breakthroughs 2025" 2. Merge the results from both searches, deduplicate by URL, and select the top 5 most relevant results 3. If Firecrawl supports fetching/extracting page content, retrieve the full content of the single most relevant result and write a 2-3 sentence summary grounded in that fetched content (not just the snippet) 4. Print the output as JSON with two keys: - "results": the top 5 deduplicated results, each with title, url, and snippet (or description) - "summary": your grounded 2-3 sentence summary of the top result (include the source url)
_probe.py
Unlock analytics
See Firecrawl's score trend, layer rankings, and competitive position.
Run completed Oct 20, 2026, 9:16 PM