From 6e3d8d90de95317bc5d5455c7343bc9b41258267 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Thu, 5 Sep 2024 07:58:58 -0700 Subject: [PATCH] Add deepseek v2.5 --- aider/website/_data/edit_leaderboard.yml | 51 ++++++++++++------------ aider/website/docs/leaderboards/index.md | 2 +- 2 files changed, 27 insertions(+), 26 deletions(-) diff --git a/aider/website/_data/edit_leaderboard.yml b/aider/website/_data/edit_leaderboard.yml index e5fd6d49f..7c3c5d484 100644 --- a/aider/website/_data/edit_leaderboard.yml +++ b/aider/website/_data/edit_leaderboard.yml @@ -317,29 +317,6 @@ seconds_per_case: 22.9 total_cost: 2.7494 -- dirname: 2024-05-09-18-57-52--deepseek-chat-v2-diff-reverted-and-helpful-assistant2 - test_cases: 133 - model: DeepSeek Chat V2 (original) - released: 2024-05-06 - edit_format: diff - commit_hash: 80a3f6d - pass_rate_1: 44.4 - pass_rate_2: 60.9 - percent_cases_well_formed: 97.0 - error_outputs: 14 - num_malformed_responses: 4 - user_asks: 2 - lazy_comments: 0 - syntax_errors: 13 - indentation_errors: 0 - exhausted_context_windows: 0 - test_timeouts: 3 - command: aider --model deepseek/deepseek-chat - date: 2024-05-09 - versions: 0.33.1-dev - seconds_per_case: 86.8 - total_cost: 0.0941 - - dirname: 2024-05-07-20-32-37--qwen1.5-110b-chat-whole test_cases: 133 model: qwen1.5-110b-chat @@ -665,7 +642,7 @@ - dirname: 2024-07-19-08-57-13--openrouter-deepseek-chat-v2-0628 test_cases: 133 - model: DeepSeek Chat V2 0628 + model: DeepSeek Chat V2 0628 (deprecated) edit_format: diff commit_hash: 96ff06e-dirty pass_rate_1: 60.9 @@ -737,7 +714,7 @@ - dirname: 2024-07-24-07-10-58--deepseek-coder2-0724-diff-direct test_cases: 133 - model: DeepSeek Coder V2 0724 + model: DeepSeek Coder V2 0724 (deprecated) edit_format: diff commit_hash: 89965bf pass_rate_1: 57.9 @@ -1017,3 +994,27 @@ versions: 0.54.13.dev seconds_per_case: 125.3 total_cost: 0.0000 + +- dirname: 2024-09-05-14-50-11--deepseek-sep5-no-shell + test_cases: 133 + model: DeepSeek Chat V2.5 + edit_format: diff + commit_hash: 1279c86 + pass_rate_1: 54.9 + pass_rate_2: 72.2 + percent_cases_well_formed: 96.2 + error_outputs: 5 + num_malformed_responses: 5 + num_with_malformed_responses: 5 + user_asks: 4 + lazy_comments: 0 + syntax_errors: 1 + indentation_errors: 0 + exhausted_context_windows: 0 + test_timeouts: 2 + command: aider --deepseek + date: 2024-09-05 + versions: 0.55.1.dev + seconds_per_case: 49.6 + total_cost: 0.0998 + \ No newline at end of file diff --git a/aider/website/docs/leaderboards/index.md b/aider/website/docs/leaderboards/index.md index 471884cc4..52f26e903 100644 --- a/aider/website/docs/leaderboards/index.md +++ b/aider/website/docs/leaderboards/index.md @@ -321,6 +321,6 @@ mod_dates = [get_last_modified_date(file) for file in files] latest_mod_date = max(mod_dates) cog.out(f"{latest_mod_date.strftime('%B %d, %Y.')}") ]]]--> -September 04, 2024. +September 05, 2024.