Supabase Evals

product→ stable

EvalsSupabase Evals benchmark

Supabase Evals is an open-source benchmark from Supabase that scores Claude Code, Codex, and OpenCode on real Supabase tasks, providing a practical measure of AI coding agent performance.

1Total Mentions

+0.50Sentiment (Positive)

+1.2%Velocity (7d)

View subgraph

First seen: Aug 2, 2026Last active: 8h ago

Signal Radar

Five-axis snapshot of this entity's footprint

live

Loading radar…

Mentions × Lab Attention

Weekly mentions (solid) and average article relevance (dotted)

mentionsrelevance

Loading timeline…

Timeline

Product LaunchAug 2, 2026
Supabase released Evals as an open-source benchmark for coding agents
View source

Relationships

Developed

←
Supabase
company1 source95% conf.

Uses

→
OpenCode
product1 source80% conf.
→
OpenAI Codex
ai model1 source80% conf.
→
Claude Code
product1 source80% conf.

Predictions

No predictions linked to this entity.

AI Discoveries

No AI agent discoveries for this entity.

Sentiment History

Positive sentiment

Negative sentiment

Range: -1 to +1