- dirname: 2024-11-09-11-09-15--Qwen2.5-Coder-32B-Instruct test_cases: 133 model: "HuggingFace via GLHF: BF16" released: 2024-11-12 edit_format: diff commit_hash: ec9982a pass_rate_1: 59.4 pass_rate_2: 71.4 percent_cases_well_formed: 94.7 error_outputs: 17 num_malformed_responses: 17 num_with_malformed_responses: 7 user_asks: 1 lazy_comments: 0 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 3 command: aider --model openai/hf:Qwen/Qwen2.5-Coder-32B-Instruct --openai-api-base https://glhf.chat/api/openai/v1 date: 2024-11-09 versions: 0.59.2.dev seconds_per_case: 22.5 total_cost: 0.0000 - dirname: 2024-11-22-18-56-13--ollama-qwen2.5-coder:32b-instruct-fp16 test_cases: 132 model: "Ollama: fp16" edit_format: diff commit_hash: f06452c-dirty, 6a0a97c-dirty, 4e9ae16-dirty, 5506d0f-dirty pass_rate_1: 58.3 pass_rate_2: 71.4 percent_cases_well_formed: 90.2 error_outputs: 27 num_malformed_responses: 26 num_with_malformed_responses: 13 user_asks: 2 lazy_comments: 0 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 0 command: aider --model ollama/qwen2.5-coder:32b-instruct-fp16 date: 2024-11-22 versions: 0.64.2.dev seconds_per_case: 119.6 total_cost: 0.0000 - dirname: 2024-11-22-14-53-26--hyperbolic-qwen25coder32binstruct test_cases: 133 model: "Hyperbolic: BF16" edit_format: diff commit_hash: f9ef161, 17aef7b-dirty pass_rate_1: 57.9 pass_rate_2: 69.2 percent_cases_well_formed: 91.7 error_outputs: 30 num_malformed_responses: 29 num_with_malformed_responses: 11 user_asks: 9 lazy_comments: 0 syntax_errors: 4 indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 2 command: aider --model openai/Qwen/Qwen2.5-Coder-32B-Instruct --openai-api-base https://api.hyperbolic.xyz/v1/ date: 2024-11-22 versions: 0.64.2.dev seconds_per_case: 33.2 total_cost: 0.0000 - dirname: 2024-11-22-17-53-35--qwen25-coder-32b-Instruct-4bit test_cases: 133 model: "mlx-community: 4bit" edit_format: diff commit_hash: a16dcab-dirty pass_rate_1: 60.2 pass_rate_2: 72.2 percent_cases_well_formed: 88.7 error_outputs: 31 num_malformed_responses: 30 num_with_malformed_responses: 15 user_asks: 6 lazy_comments: 0 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 1 test_timeouts: 0 command: aider --model openai/mlx-community/Qwen2.5-Coder-32B-Instruct-4bit date: 2024-11-23 versions: 0.64.2.dev seconds_per_case: 53.4 total_cost: 0.0000 - dirname: 2024-11-23-15-07-20--qwen25-coder-32b-Instruct-8bit test_cases: 133 model: "mlx-community: 8bit" edit_format: diff commit_hash: a16dcab-dirty pass_rate_1: 59.4 pass_rate_2: 72.2 percent_cases_well_formed: 92.5 error_outputs: 20 num_malformed_responses: 15 num_with_malformed_responses: 10 user_asks: 7 lazy_comments: 0 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 5 test_timeouts: 2 command: aider --model openai/mlx-community/Qwen2.5-Coder-32B-Instruct-8bit date: 2024-11-23 versions: 0.64.2.dev seconds_per_case: 98.4 total_cost: 0.0000 - dirname: 2024-11-24-22-18-18--or-all-or-fixed-blank-messages2 test_cases: 133 model: "OpenRouter: multiple" edit_format: diff commit_hash: 0c59d32 pass_rate_1: 57.1 pass_rate_2: 67.7 percent_cases_well_formed: 95.5 error_outputs: 56 num_malformed_responses: 10 num_with_malformed_responses: 6 user_asks: 14 lazy_comments: 0 syntax_errors: 6 indentation_errors: 0 exhausted_context_windows: 3 test_timeouts: 1 command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct date: 2024-11-24 versions: 0.64.2.dev seconds_per_case: 21.2 total_cost: 0.1420 - dirname: 2024-11-23-21-08-53--ollama-qwen2.5-coder:32b-instruct-q4_K_M-8kctx test_cases: 133 model: "Ollama: q4_K_M" edit_format: diff commit_hash: baa1335-dirty, e63df83-dirty, ff8c1aa-dirty pass_rate_1: 54.9 pass_rate_2: 66.9 percent_cases_well_formed: 94.0 error_outputs: 21 num_malformed_responses: 21 num_with_malformed_responses: 8 user_asks: 5 lazy_comments: 0 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 3 command: aider --model ollama/qwen2.5-coder:32b-instruct-q4_K_M date: 2024-11-23 versions: 0.64.2.dev seconds_per_case: 35.7 total_cost: 0.0000 - dirname: 2024-11-24-02-23-32--deepinfra-qwen-diff test_cases: 133 model: "Deepinfra: BF16" edit_format: diff commit_hash: bb78e2f pass_rate_1: 58.6 pass_rate_2: 72.2 percent_cases_well_formed: 94.7 error_outputs: 15 num_malformed_responses: 13 num_with_malformed_responses: 7 user_asks: 3 lazy_comments: 0 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 2 test_timeouts: 3 command: aider --model deepinfra/Qwen/Qwen2.5-Coder-32B-Instruct date: 2024-11-24 versions: 0.64.2.dev seconds_per_case: 17.5 total_cost: 0.0000 - dirname: 2024-11-24-04-12-58--fireworks-qwen-diff test_cases: 133 model: "Fireworks: unknown" edit_format: diff commit_hash: 757eac0 pass_rate_1: 57.9 pass_rate_2: 72.2 percent_cases_well_formed: 94.0 error_outputs: 23 num_malformed_responses: 19 num_with_malformed_responses: 8 user_asks: 8 lazy_comments: 0 syntax_errors: 6 indentation_errors: 0 exhausted_context_windows: 4 test_timeouts: 1 command: aider --model fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct date: 2024-11-24 versions: 0.64.2.dev seconds_per_case: 10.4 total_cost: 0.5759 - dirname: 2024-11-24-02-04-59--ollama-qwen2.5-coder:32b-instruct-q2_K-8kctx test_cases: 133 model: "Ollama: q2_K" edit_format: diff commit_hash: 757eac0, bb78e2f, 8d0ba40-dirty, 1d09e96 pass_rate_1: 48.9 pass_rate_2: 61.7 percent_cases_well_formed: 91.7 error_outputs: 32 num_malformed_responses: 32 num_with_malformed_responses: 11 user_asks: 8 lazy_comments: 0 syntax_errors: 0 indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 1 command: aider --model ollama/qwen2.5-coder:32b-instruct-q2_K date: 2024-11-24 versions: 0.64.2.dev seconds_per_case: 97.8 total_cost: 0.0000 - dirname: 2024-11-24-14-56-49--qwen25-32b-or-fireworks test_cases: 133 model: "Fireworks via OpenRouter: unknown" edit_format: diff commit_hash: c2f184f pass_rate_1: 55.6 pass_rate_2: 67.7 percent_cases_well_formed: 94.0 error_outputs: 39 num_malformed_responses: 24 num_with_malformed_responses: 8 user_asks: 13 lazy_comments: 0 syntax_errors: 1 indentation_errors: 1 exhausted_context_windows: 7 test_timeouts: 4 command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct date: 2024-11-24 versions: 0.64.2.dev seconds_per_case: 16.1 total_cost: 0.1391 - dirname: 2024-11-24-22-03-19--or-hyperbolic-or-fixed-blank-messages2 test_cases: 133 model: "Hyperbolic via OpenRouter: BF16" edit_format: diff commit_hash: 0c59d32 pass_rate_1: 55.6 pass_rate_2: 68.4 percent_cases_well_formed: 89.5 error_outputs: 28 num_malformed_responses: 24 num_with_malformed_responses: 14 user_asks: 29 lazy_comments: 0 syntax_errors: 1 indentation_errors: 0 exhausted_context_windows: 4 test_timeouts: 1 command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct date: 2024-11-24 versions: 0.64.2.dev seconds_per_case: 41.5 total_cost: 0.1402 - dirname: 2024-11-24-15-00-50--qwen25-32b-or-deepinfra test_cases: 133 model: "Deepinfra via OpenRouter: BF16" edit_format: diff commit_hash: c2f184f pass_rate_1: 57.1 pass_rate_2: 69.9 percent_cases_well_formed: 89.5 error_outputs: 35 num_malformed_responses: 31 num_with_malformed_responses: 14 user_asks: 11 lazy_comments: 0 syntax_errors: 1 indentation_errors: 1 exhausted_context_windows: 4 test_timeouts: 1 command: aider --model openrouter/qwen/qwen-2.5-coder-32b-instruct date: 2024-11-24 versions: 0.64.2.dev seconds_per_case: 28.5 total_cost: 0.1390 - dirname: 2024-11-26-03-15-06--ollama-qwen2.5-coder:32b-instruct-fp16-2kctx test_cases: 132 model: "Ollama: fp16, 2k ctx" edit_format: diff commit_hash: 68be6c5-dirty, 554d274, 2ff3a23, 2ff3a23-dirty, 61759f9, dd48b74, 3ebd47d-dirty pass_rate_1: 43.2 pass_rate_2: 51.9 percent_cases_well_formed: 46.2 error_outputs: 171 num_malformed_responses: 165 num_with_malformed_responses: 71 user_asks: 97 lazy_comments: 2 syntax_errors: 4 indentation_errors: 0 exhausted_context_windows: 0 test_timeouts: 0 command: "aider --model ollama/qwen2.5-coder:32b-instruct-fp16 # num_ctx: 2048" date: 2024-11-26 versions: 0.64.2.dev,0.65.1.dev seconds_per_case: 188.6 total_cost: 0.0000