Skip to content

Publish code-review vanilla baseline (claude-haiku-4-5, repeat=5) #684

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

Open
gggdttt wants to merge 5 commits into
base: main
Choose a base branch
from
+231 −2
Open

Publish code-review vanilla baseline (claude-haiku-4-5, repeat=5) #684

Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
160a17d
Update leaderboard: GitHub Copilot CLI (claude-haiku-4.5) - Run 28105…
github-actions[bot] Jun 24, 2026
d77f7a9
Update leaderboard: GitHub Copilot CLI (claude-haiku-4.5) - Run 28106…
github-actions[bot] Jun 24, 2026
5f4e41d
Update leaderboard: GitHub Copilot CLI (claude-haiku-4.5) - Run 28107…
github-actions[bot] Jun 24, 2026
2959486
Update leaderboard: GitHub Copilot CLI (claude-haiku-4.5) - Run 28107…
github-actions[bot] Jun 24, 2026
b8e0939
Update leaderboard: GitHub Copilot CLI (claude-haiku-4.5) - Run 28108…
github-actions[bot] Jun 24, 2026
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
233 changes: 231 additions & 2 deletions docs/_data/code-review.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,233 @@
{
"runs": [],
"aggregate": []
"runs": [
{
"total": 81,
"date": "2026-06-24",
"model": "claude-haiku-4-5",
"agent_name": "GitHub Copilot",
"category": "code-review",
"average_duration": 51.9,
"average_prompt_tokens": 113035.8,
"average_completion_tokens": 1590.2,
"average_llm_duration": 0.0,
"average_tool_usage": {
"report_intent": 0.93,
"bash": 3.19,
"view": 1.16,
"create": 0.8,
"read_bash": 0.37,
"stop_bash": 0.21,
"write_bash": 0.07,
"task": 0.01
},
"github_run_id": "28105886936",
"experiment": null,
"benchmark_version": "0.5.6",
"generated_comment_count": 251,
"expected_comment_count": 216,
"matched_comment_count": 51,
"incorrect_comment_count": 200,
"missed_comment_count": 165,
"precision": 0.203,
"recall": 0.236,
"f1": 0.218,
"f_beta_05": 0.209,
"f_beta_2": 0.229,
"macro_precision": 0.245,
"macro_recall": 0.329,
"macro_f1": 0.256,
"macro_f_beta_05": 0.242,
"macro_f_beta_2": 0.286,
"severity_mae": 0.784,
"valid_review_output_rate": 1.0
},
{
"total": 81,
"date": "2026-06-24",
"model": "claude-haiku-4-5",
"agent_name": "GitHub Copilot",
"category": "code-review",
"average_duration": 53.0,
"average_prompt_tokens": 124801.2,
"average_completion_tokens": 1724.0,
"average_llm_duration": 0.0,
"average_tool_usage": {
"report_intent": 0.94,
"bash": 3.65,
"view": 1.32,
"create": 0.73,
"read_bash": 0.37,
"stop_bash": 0.35,
"write_bash": 0.02,
"task": 0.01
},
"github_run_id": "28106565168",
"experiment": null,
"benchmark_version": "0.5.6",
"generated_comment_count": 222,
"expected_comment_count": 216,
"matched_comment_count": 40,
"incorrect_comment_count": 182,
"missed_comment_count": 176,
"precision": 0.18,
"recall": 0.185,
"f1": 0.183,
"f_beta_05": 0.181,
"f_beta_2": 0.184,
"macro_precision": 0.226,
"macro_recall": 0.263,
"macro_f1": 0.217,
"macro_f_beta_05": 0.213,
"macro_f_beta_2": 0.235,
"severity_mae": 0.725,
"valid_review_output_rate": 1.0
},
{
"total": 81,
"date": "2026-06-24",
"model": "claude-haiku-4-5",
"agent_name": "GitHub Copilot",
"category": "code-review",
"average_duration": 53.6,
"average_prompt_tokens": 121482.7,
"average_completion_tokens": 1617.1,
"average_llm_duration": 0.0,
"average_tool_usage": {
"report_intent": 0.95,
"bash": 3.36,
"create": 0.85,
"stop_bash": 0.41,
"view": 1.25,
"read_bash": 0.47,
"write_bash": 0.01
},
"github_run_id": "28107173987",
"experiment": null,
"benchmark_version": "0.5.6",
"generated_comment_count": 230,
"expected_comment_count": 216,
"matched_comment_count": 48,
"incorrect_comment_count": 182,
"missed_comment_count": 168,
"precision": 0.209,
"recall": 0.222,
"f1": 0.215,
"f_beta_05": 0.211,
"f_beta_2": 0.219,
"macro_precision": 0.242,
"macro_recall": 0.292,
"macro_f1": 0.229,
"macro_f_beta_05": 0.219,
"macro_f_beta_2": 0.254,
"severity_mae": 0.729,
"valid_review_output_rate": 1.0
},
{
"total": 81,
"date": "2026-06-24",
"model": "claude-haiku-4-5",
"agent_name": "GitHub Copilot",
"category": "code-review",
"average_duration": 50.0,
"average_prompt_tokens": 112477.8,
"average_completion_tokens": 1602.7,
"average_llm_duration": 0.0,
"average_tool_usage": {
"report_intent": 0.93,
"bash": 3.02,
"create": 0.8,
"read_bash": 0.43,
"stop_bash": 0.32,
"view": 0.98,
"write_bash": 0.06
},
"github_run_id": "28107756834",
"experiment": null,
"benchmark_version": "0.5.6",
"generated_comment_count": 242,
"expected_comment_count": 216,
"matched_comment_count": 47,
"incorrect_comment_count": 195,
"missed_comment_count": 169,
"precision": 0.194,
"recall": 0.218,
"f1": 0.205,
"f_beta_05": 0.198,
"f_beta_2": 0.212,
"macro_precision": 0.216,
"macro_recall": 0.285,
"macro_f1": 0.223,
"macro_f_beta_05": 0.21,
"macro_f_beta_2": 0.25,
"severity_mae": 0.681,
"valid_review_output_rate": 1.0
},
{
"total": 81,
"date": "2026-06-24",
"model": "claude-haiku-4-5",
"agent_name": "GitHub Copilot",
"category": "code-review",
"average_duration": 53.9,
"average_prompt_tokens": 119386.4,
"average_completion_tokens": 1680.6,
"average_llm_duration": 0.0,
"average_tool_usage": {
"report_intent": 0.93,
"bash": 3.16,
"create": 0.83,
"read_bash": 0.42,
"stop_bash": 0.37,
"view": 1.42,
"write_bash": 0.02,
"task": 0.01
},
"github_run_id": "28108519915",
"experiment": null,
"benchmark_version": "0.5.6",
"generated_comment_count": 292,
"expected_comment_count": 216,
"matched_comment_count": 48,
"incorrect_comment_count": 244,
"missed_comment_count": 168,
"precision": 0.164,
"recall": 0.222,
"f1": 0.189,
"f_beta_05": 0.173,
"f_beta_2": 0.208,
"macro_precision": 0.205,
"macro_recall": 0.304,
"macro_f1": 0.216,
"macro_f_beta_05": 0.196,
"macro_f_beta_2": 0.254,
"severity_mae": 0.729,
"valid_review_output_rate": 1.0
}
],
"aggregate": [
{
"model": "claude-haiku-4-5",
"agent_name": "GitHub Copilot",
"category": "code-review",
"experiment": null,
"total": 81,
"num_runs": 5,
"average_duration": 52.48,
"benchmark_version": "0.5.6",
"f1": 0.202,
"f1_ci_low": 0.189,
"f1_ci_high": 0.213,
"f_beta_05": 0.1944,
"f_beta_2": 0.2104,
"precision": 0.19,
"recall": 0.2166,
"macro_f1": 0.228,
"macro_f1_ci_low": 0.219,
"macro_f1_ci_high": 0.248,
"macro_f_beta_05": 0.21600000000000003,
"macro_f_beta_2": 0.25579999999999997,
"macro_precision": 0.22679999999999997,
"macro_recall": 0.2946
}
]
}
Loading