google/gemini-2.0-flash -> 2.5

docs/guides/about_the_framework.md

@@ -39,7 +39,7 @@ The Python CLI entry point is `run-evals`, defined in
 run-evals --json ./eval_set.json
 
 # Mode 2: Direct CLI arguments (what you used in Part 1)
-run-evals --task question_answer --model google/gemini-2.0-flash --dataset samples.json
+run-evals --task question_answer --model google/gemini-2.5-flash --dataset samples.json
 ```
 
 ### JSON runner

docs/guides/using_the_cli.md

@@ -35,7 +35,7 @@ my-project/
 - The starter task uses `func: analyze_codebase` — fine for a smoke test, but
   you'll want to change `func` to match your eval type (`question_answer`,
   `bug_fix`, `code_gen`, etc.)
-- The job defaults to `google/gemini-2.0-flash`. Update `models:` to the
+- The job defaults to `google/gemini-2.5-flash`. Update `models:` to the
   provider(s) you want to test.
 - `files` points at `../../` (your project root). Update if your workspace
   lives elsewhere.

packages/devals_cli/example/evals/jobs/local_dev.yaml

@@ -40,7 +40,7 @@
 # Which models to evaluate. Format: "provider/model-name"
 # If omitted, falls back to DEFAULT_MODELS from the Python registries.
 models:
-  - google/gemini-2.0-flash
+  - google/gemini-2.5-flash
 
 # =============================================================================
 # VARIANTS (Optional)

packages/devals_cli/lib/src/commands/init_command.dart

@@ -67,7 +67,7 @@ class InitCommand extends Command<int> {
           File(jobPath).writeAsStringSync(
             initJobTemplate(
               name: 'local_dev',
-              models: ['google/gemini-2.0-flash'],
+              models: ['google/gemini-2.5-flash'],
               tasks: ['get_started'],
             ),
           );