chore: Add DeepSeek R1 benchmark results

This commit is contained in:
Paul Gauthier 2025-06-09 06:34:26 -07:00 committed by Paul Gauthier (aider)
parent e256ffd2c6
commit 47ddce3e1b

View file

@ -1535,3 +1535,31 @@
versions: 0.84.1.dev
seconds_per_case: 200.3
total_cost: 49.8822
- dirname: 2025-06-06-16-47-07--r1-diff
test_cases: 224
model: DeepSeek R1 (0528)
edit_format: diff
commit_hash: 4c161f9-dirty
pass_rate_1: 34.4
pass_rate_2: 71.4
pass_num_1: 77
pass_num_2: 160
percent_cases_well_formed: 94.6
error_outputs: 28
num_malformed_responses: 15
num_with_malformed_responses: 12
user_asks: 105
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
prompt_tokens: 2644169
completion_tokens: 1842168
test_timeouts: 2
total_tests: 225
command: aider --model deepseek/deepseek-reasoner
date: 2025-06-06
versions: 0.84.1.dev
seconds_per_case: 716.6
total_cost: 4.8016