From dc7e61f3c996e24e7ecda6cbf074b240a86e01e8 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Tue, 7 May 2024 09:38:46 -0700 Subject: [PATCH] added deepseek-chat v2 (diff) to leaderboard --- _data/edit_leaderboard.yml | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/_data/edit_leaderboard.yml b/_data/edit_leaderboard.yml index abca0dfb4..658343d69 100644 --- a/_data/edit_leaderboard.yml +++ b/_data/edit_leaderboard.yml @@ -315,7 +315,7 @@ total_cost: 2.7494 - dirname: 2024-05-07-12-55-06--deepseek-chat-v2-whole test_cases: 133 - model: deepseek-chat v2 + model: deepseek-chat v2 (whole) edit_format: whole commit_hash: b1cae73, db994fb pass_rate_1: 50.4 @@ -329,9 +329,29 @@ indentation_errors: 2 exhausted_context_windows: 0 test_timeouts: 1 - command: aider --model openai/deepseek-chat + command: aider --model openai/deepseek-chat --edit-format whole date: 2024-05-07 versions: 0.31.2-dev seconds_per_case: 42.4 total_cost: 0.0000 - \ No newline at end of file +- dirname: 2024-05-07-15-49-02--deepseek-chat-v2-diff-sysex-sysrem + test_cases: 133 + model: deepseek-chat v2 (diff) + edit_format: diff + commit_hash: e9da401 + pass_rate_1: 42.9 + pass_rate_2: 55.6 + percent_cases_well_formed: 97.7 + error_outputs: 11 + num_malformed_responses: 3 + user_asks: 2 + lazy_comments: 0 + syntax_errors: 2 + indentation_errors: 0 + exhausted_context_windows: 0 + test_timeouts: 4 + command: aider --model openai/deepseek-chat + date: 2024-05-07 + versions: 0.31.2-dev + seconds_per_case: 53.8 + total_cost: 0.0000 \ No newline at end of file