From e256ffd2c689446239f1a85e1b03b807dbe5e5f6 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Mon, 9 Jun 2025 06:28:12 -0700 Subject: [PATCH] chore: Add Gemini 2.5 Pro results to leaderboard --- aider/website/_data/polyglot_leaderboard.yml | 59 +++++++++++++++++++- 1 file changed, 58 insertions(+), 1 deletion(-) diff --git a/aider/website/_data/polyglot_leaderboard.yml b/aider/website/_data/polyglot_leaderboard.yml index 51676fc72..fc2a7862c 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -1477,4 +1477,61 @@ date: 2025-05-25 versions: 0.83.3.dev seconds_per_case: 53.9 - total_cost: 8.5625 \ No newline at end of file + total_cost: 8.5625 + +- dirname: 2025-06-06-18-38-56--gemini0605-diff-fenced + test_cases: 225 + model: gemini-2.5-pro-preview-06-05 (default think) + edit_format: diff-fenced + commit_hash: 4c161f9-dirty + pass_rate_1: 44.9 + pass_rate_2: 79.1 + pass_num_1: 101 + pass_num_2: 178 + percent_cases_well_formed: 100.0 + error_outputs: 4 + num_malformed_responses: 0 + num_with_malformed_responses: 0 + user_asks: 105 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 4 + prompt_tokens: 2751296 + completion_tokens: 4142197 + test_timeouts: 1 + total_tests: 225 + command: aider --model gemini/gemini-2.5-pro-preview-06-05 + date: 2025-06-06 + versions: 0.84.1.dev + seconds_per_case: 175.2 + total_cost: 45.5961 + +- dirname: 2025-06-06-16-36-21--gemini0605-32k-think-diff-fenced + test_cases: 225 + model: gemini-2.5-pro-preview-06-05 (32k think) + edit_format: diff-fenced + commit_hash: f827f22 + thinking_tokens: 32768 + pass_rate_1: 46.2 + pass_rate_2: 83.1 + pass_num_1: 104 + pass_num_2: 187 + percent_cases_well_formed: 99.6 + error_outputs: 1 + num_malformed_responses: 1 + num_with_malformed_responses: 1 + user_asks: 112 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 0 + prompt_tokens: 2719961 + completion_tokens: 4648227 + test_timeouts: 0 + total_tests: 225 + command: aider --model gemini/gemini-2.5-pro-preview-06-05 --thinking-tokens 32k + date: 2025-06-06 + versions: 0.84.1.dev + seconds_per_case: 200.3 + total_cost: 49.8822 \ No newline at end of file