added DeepSeek R1 + DeepSeek V3 benchmark

This commit is contained in:
Sung-jin Brian Hong 2025-01-26 10:36:49 +09:00
parent 2b59badde7
commit 0fe03fd394
No known key found for this signature in database
GPG key ID: F1870D7690DF681A

View file

@ -1,5 +1,32 @@
- dirname: 2025-01-25-13-53-23--deepseek-r1-v3
test_cases: 225
model: deepseek/deepseek-reasoner
edit_format: architect
commit_hash: b276d48-dirty
editor_model: deepseek/deepseek-chat
editor_edit_format: editor-diff
pass_rate_1: 30.7
pass_rate_2: 59.1
pass_num_1: 69
pass_num_2: 133
percent_cases_well_formed: 100.0
error_outputs: 13
num_malformed_responses: 0
num_with_malformed_responses: 0
user_asks: 388
lazy_comments: 1
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 0
test_timeouts: 4
total_tests: 225
command: aider --model deepseek/deepseek-reasoner
date: 2025-01-25
versions: 0.72.3.dev
seconds_per_case: 949.4
total_cost: 6.3330
- dirname: 2025-01-23-19-14-48--r1-architect-sonnet
test_cases: 225