Unit eval GPT-5 and Gemini 3 Pro (#43916)

Richard Feldman created 17 hours ago

Follow-up to #43907

Release Notes:

- N/A

Change summary

.github/workflows/run_cron_unit_evals.yml            | 2 ++
tooling/xtask/src/tasks/workflows/run_agent_evals.rs | 2 ++
2 files changed, 4 insertions(+)

Detailed changes

.github/workflows/run_cron_unit_evals.yml

@@ -18,6 +18,8 @@ jobs:
         model:
         - anthropic/claude-sonnet-4-5-latest
         - anthropic/claude-opus-4-5-latest
+        - google/gemini-3-pro
+        - openai/gpt-5
       fail-fast: false
     steps:
     - name: steps::checkout_repo

tooling/xtask/src/tasks/workflows/run_agent_evals.rs

@@ -123,6 +123,8 @@ fn cron_unit_evals() -> NamedJob {
 const UNIT_EVAL_MODELS: &[&str] = &[
     "anthropic/claude-sonnet-4-5-latest",
     "anthropic/claude-opus-4-5-latest",
+    "google/gemini-3-pro",
+    "openai/gpt-5",
 ];
 
 fn cron_unit_evals_job() -> Job {