Is it possible to select the reasoning effort of GPT-5 in OpenCode? #1263

Closed
opened 2026-02-16 17:30:11 -05:00 by yindo · 0 comments
Owner

Originally created by @VictorTaelin on GitHub (Aug 12, 2025).

The performance of the GPT-5 model varies greatly based on the reasoning-effort parameter. With minimum, it is a very unreliable, low rank model. With high, it is the #1 on many benchmarks.

Is it possible to make sure / assert that OpenCode is using GPT-5 with high reasoning effort?

Originally created by @VictorTaelin on GitHub (Aug 12, 2025). The performance of the GPT-5 model varies greatly based on the reasoning-effort parameter. With minimum, it is a very unreliable, low rank model. With high, it is the #1 on many benchmarks. Is it possible to make sure / assert that OpenCode is using GPT-5 with high reasoning effort?
yindo closed this issue 2026-02-16 17:30:11 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#1263