From 32d025bcf2f43abd4033cbeda390b77d0fc9fbca Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Mon, 20 Jan 2025 11:37:09 -0800 Subject: [PATCH] r1 leaderboard --- aider/website/_data/polyglot_leaderboard.yml | 28 +++++++++++++++++++- 1 file changed, 27 insertions(+), 1 deletion(-) diff --git a/aider/website/_data/polyglot_leaderboard.yml b/aider/website/_data/polyglot_leaderboard.yml index eb2b97b19..c4de84159 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -386,4 +386,30 @@ date: 2025-01-13 versions: 0.71.2.dev seconds_per_case: 9.3 - total_cost: 1.9834 \ No newline at end of file + total_cost: 1.9834 + +- dirname: 2025-01-20-19-11-38--ds-turns-upd-cur-msgs-fix-with-summarizer + test_cases: 225 + model: DeepSeek R1 + edit_format: diff + commit_hash: 5650697-dirty + pass_rate_1: 26.7 + pass_rate_2: 56.9 + pass_num_1: 60 + pass_num_2: 128 + percent_cases_well_formed: 96.9 + error_outputs: 8 + num_malformed_responses: 7 + num_with_malformed_responses: 7 + user_asks: 15 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 1 + test_timeouts: 5 + total_tests: 225 + command: aider --model deepseek/deepseek-reasoner + date: 2025-01-20 + versions: 0.71.2.dev + seconds_per_case: 113.7 + total_cost: 5.4193 \ No newline at end of file