diff --git a/HISTORY.md b/HISTORY.md index 47fcea2df..88ae32927 100644 --- a/HISTORY.md +++ b/HISTORY.md @@ -2,6 +2,7 @@ ### main branch +- Support for o1 models. - Support for running without git installed. - Show hints about AI! and AI? when user makes AI comments. - Ask 10% of users to opt-in to analytics. diff --git a/aider/models.py b/aider/models.py index 831bf4bd6..885fef5f6 100644 --- a/aider/models.py +++ b/aider/models.py @@ -665,6 +665,13 @@ MODEL_SETTINGS = [ examples_as_sys_msg=True, reminder="sys", ), + ModelSettings( + "openrouter/deepseek/deepseek-chat", + "diff", + use_repo_map=True, + examples_as_sys_msg=True, + reminder="sys", + ), ModelSettings( "openrouter/openai/gpt-4o", "diff", diff --git a/aider/website/_data/polyglot_leaderboard.yml b/aider/website/_data/polyglot_leaderboard.yml index 9bc818778..8b81d834c 100644 --- a/aider/website/_data/polyglot_leaderboard.yml +++ b/aider/website/_data/polyglot_leaderboard.yml @@ -152,4 +152,30 @@ date: 2024-12-21 versions: 0.69.2.dev seconds_per_case: 31.8 - total_cost: 6.0583 \ No newline at end of file + total_cost: 6.0583 + +- dirname: 2024-12-22-13-22-32--polyglot-qwen-diff + test_cases: 225 + model: Qwen2.5-Coder-32B-Instruct + edit_format: diff + commit_hash: 6d7e8be-dirty + pass_rate_1: 4.4 + pass_rate_2: 8.0 + pass_num_1: 10 + pass_num_2: 18 + percent_cases_well_formed: 71.6 + error_outputs: 158 + num_malformed_responses: 148 + num_with_malformed_responses: 64 + user_asks: 132 + lazy_comments: 0 + syntax_errors: 0 + indentation_errors: 0 + exhausted_context_windows: 1 + test_timeouts: 2 + total_tests: 225 + command: "aider --model openai/Qwen/Qwen2.5-Coder-32B-Instruct # via hyperbolic" + date: 2024-12-22 + versions: 0.69.2.dev + seconds_per_case: 84.4 + total_cost: 0.0000 \ No newline at end of file diff --git a/aider/website/_posts/2024-12-21-polyglot.md b/aider/website/_posts/2024-12-21-polyglot.md index 8218631b9..eadc10e38 100644 --- a/aider/website/_posts/2024-12-21-polyglot.md +++ b/aider/website/_posts/2024-12-21-polyglot.md @@ -152,7 +152,7 @@ how long it will take for this new benchmark to saturate. ## Benchmark problems The 225 coding problems are available in the -[aider polyglot benchmark repo]() +[aider polyglot benchmark repo](https://github.com/Aider-AI/polyglot-benchmark) on GitHub. diff --git a/aider/website/assets/o1-polyglot.jpg b/aider/website/assets/o1-polyglot.jpg new file mode 100644 index 000000000..8945eb1af Binary files /dev/null and b/aider/website/assets/o1-polyglot.jpg differ