Skip to content

Create new_tests_results.md #147

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
artzhuravel merged 1 commit into from
Apr 11, 2026
Merged

Create new_tests_results.md #147

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions experiments/kdd 2026/new_tests_results.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,17 @@
# Results: Newly Added Tests

Assertion-weighted mean scores (0-100) on the **36 newly added tests** only: 17 Box, 5 Google Calendar, 7 Linear, and 6 Slack. All runs included API documentation.

| Model | Weighted Mean
|---|---|---|
| openai/gpt-5 | 88.10
| openai/gpt-5-mini | 87.61
| deepseek/deepseek-v3.2 | 84.26
| mistralai/devstral-2512 | 80.38
| google/gemini-3.1-pro-preview | 77.69
| moonshotai/kimi-k2-0905 | 74.06
| qwen/qwen3-vl-235b-a22b-instruct | 74.06
| google/gemini-3-flash-preview | 67.78
| x-ai/grok-4.1-fast | 65.44
| meta-llama/llama-4-scout | 28.63
| openai/gpt-oss-120b | 27.90
Loading