Convex

Convex

convex.devDatabaseGitHub CopilotGitHub Copilot
75/ 100
B
Score Breakdown75%

Lost points on 5 checks

  • cost6/10
  • time5/15
  • efficiency0/10
  • zero errors0/5
  • OpenAPI0/14
Eval Score (70% weight)71%
cost$0.16 ($0.10–$0.20, great)+6
time132s (120s–180s, good)+5
efficiency28 tool calls (>25, inefficient)+0
found docsTouched docs at docs.convex.dev: yes (14 matching tool calls)+10
zero errorsTool outputs with errors/tracebacks: 1+0
syntax validCode compiles/parses correctly+5
created filesGenerated files: 10 (need ≥1)+10
full executionMethod: full_execution, Exit: 0+35
Checklist Score (30% weight)86%
Context7
Link+14
llms.txt
Link+14
MCP Server
Link+14
Typed SDK
Link+14
OpenAPI
+0
Agent Skills
Link+14
CLI
Link+14

Checklist determined by AI. If something looks wrong, .

Final Score
A: >=90%B: 75-89%C: 55-74%D: <55%
(71 × 0.7) + (86 × 0.3)= 75%
Replay
Using https://docs.convex.dev, complete the following task:

Using the Convex Python SDK, build me a script that performs CRUD operations:

1. Install the official Convex Python SDK (pip install)
2. Connect to Convex using the SDK
3. Create a table/collection called "leaderboard_*****" with fields: id, name (string), score (number), created_at (timestamp)
4. Insert 3 records: ("Alice", 95), ("Bob", 87), ("Charlie", 92)
5. Query all records sorted by score descending
6. Update Bob's score to 91
7. Delete Charlie's record
8. Query again and print the final state as JSON

You MUST use the official Convex Python SDK — do not make raw HTTP/REST calls.
package.json

Unlock analytics

See Convex's score trend, layer rankings, and competitive position.

Run completed Oct 26, 2026, 6:20 PM