Merge branch 'main' into polyglot-qwen2.5-coder-32b-instruct-whole-results

This commit is contained in:
paul-gauthier 2025-01-03 09:35:14 -04:00 committed by GitHub
commit 42f6c20ada
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
33 changed files with 1349 additions and 1103 deletions

View file

@ -3457,3 +3457,91 @@
Paul Gauthier (aider): 207
start_tag: v0.68.0
total_lines: 305
- aider_percentage: 74.22
aider_total: 875
end_date: '2024-12-26'
end_tag: v0.70.0
file_counts:
aider/__init__.py:
Paul Gauthier: 1
aider/analytics.py:
Paul Gauthier: 6
Paul Gauthier (aider): 41
aider/args.py:
Evan Johnson: 2
aider/coders/search_replace.py:
Paul Gauthier: 5
aider/commands.py:
Paul Gauthier (aider): 41
aider/help_pats.py:
Paul Gauthier: 3
aider/io.py:
Paul Gauthier: 7
Paul Gauthier (aider): 9
aider/main.py:
Paul Gauthier: 15
Paul Gauthier (aider): 5
apaz-cli: 3
mdk: 6
aider/models.py:
Paul Gauthier: 29
aider/repo.py:
Paul Gauthier: 14
aider/utils.py:
Paul Gauthier: 2
aider/watch.py:
Paul Gauthier: 13
aider/website/_includes/head_custom.html:
Paul Gauthier (aider): 4
aider/website/_includes/leaderboard.js:
Paul Gauthier (aider): 14
aider/website/docs/leaderboards/index.md:
Paul Gauthier: 28
Paul Gauthier (aider): 2
benchmark/Dockerfile:
Paul Gauthier: 8
Paul Gauthier (aider): 43
benchmark/benchmark.py:
Paul Gauthier: 69
Paul Gauthier (aider): 153
benchmark/clone-exercism.sh:
Paul Gauthier: 2
Paul Gauthier (aider): 18
benchmark/cpp-test.sh:
Paul Gauthier: 10
Paul Gauthier (aider): 1
benchmark/docker.sh:
Paul Gauthier (aider): 4
benchmark/install-docker-ubuntu.sh:
Paul Gauthier (aider): 63
benchmark/npm-test.sh:
Paul Gauthier: 10
Paul Gauthier (aider): 3
benchmark/problem_stats.py:
Paul Gauthier: 35
Paul Gauthier (aider): 318
benchmark/rsync.sh:
Paul Gauthier: 7
Paul Gauthier (aider): 26
scripts/blame.py:
Paul Gauthier (aider): 6
scripts/my_models.py:
Paul Gauthier (aider): 95
scripts/update-blame.sh:
Paul Gauthier (aider): 3
scripts/update-docs.sh:
Paul Gauthier: 1
tests/basic/test_analytics.py:
Paul Gauthier (aider): 19
tests/basic/test_main.py:
Paul Gauthier (aider): 7
tests/basic/test_sanity_check_repo.py:
mdk: 28
grand_total:
Evan Johnson: 2
Paul Gauthier: 265
Paul Gauthier (aider): 875
apaz-cli: 3
mdk: 34
start_tag: v0.69.0
total_lines: 1179

View file

@ -257,10 +257,36 @@
versions: 0.69.2.dev
seconds_per_case: 12.2
total_cost: 0.0000
- dirname: 2024-12-23-01-11-56--yi-test
test_cases: 225
model: yi-lightning
edit_format: whole
commit_hash: 2b1625e
pass_rate_1: 5.8
pass_rate_2: 12.9
pass_num_1: 13
pass_num_2: 29
percent_cases_well_formed: 92.9
error_outputs: 87
num_malformed_responses: 72
num_with_malformed_responses: 16
user_asks: 107
lazy_comments: 0
syntax_errors: 0
indentation_errors: 0
exhausted_context_windows: 1
test_timeouts: 6
total_tests: 225
command: aider --model openai/yi-lightning
date: 2024-12-23
versions: 0.69.2.dev
seconds_per_case: 146.7
total_cost: 0.0000
- dirname: 2024-12-25-13-31-51--deepseekv3preview-diff2
test_cases: 225
model: DeepSeek Chat V3 Preview
model: DeepSeek Chat V3
edit_format: diff
commit_hash: 0a23c4a-dirty
pass_rate_1: 22.7
@ -308,4 +334,5 @@
date: 2024-12-26
versions: 0.69.2.dev
seconds_per_case: 42.0
total_cost: 0.0000
total_cost: 0.0000