mirror of
https://github.com/Aider-AI/aider.git
synced 2025-05-30 09:14:59 +00:00
chore: Update polyglot leaderboard data with new model test results
This commit is contained in:
parent
52162a5604
commit
f111ab48fb
2 changed files with 31 additions and 3 deletions
|
@ -677,7 +677,7 @@
|
|||
|
||||
- dirname: 2025-03-06-17-40-24--qwq32b-diff-temp-topp-ex-sys-remind-user-for-real
|
||||
test_cases: 225
|
||||
model: qwq-32b
|
||||
model: QwQ-32B
|
||||
edit_format: diff
|
||||
commit_hash: 51d118f-dirty
|
||||
pass_rate_1: 8.0
|
||||
|
@ -699,4 +699,32 @@
|
|||
date: 2025-03-06
|
||||
versions: 0.75.3.dev
|
||||
seconds_per_case: 228.6
|
||||
total_cost: 0.0000
|
||||
total_cost: 0.0000
|
||||
|
||||
- dirname: 2025-03-07-15-11-27--qwq32b-arch-temp-topp-again
|
||||
test_cases: 225
|
||||
model: QwQ-32B + Qwen 2.5 Coder Instruct
|
||||
edit_format: architect
|
||||
commit_hash: 52162a5
|
||||
editor_model: fireworks_ai/accounts/fireworks/models/qwen2p5-coder-32b-instruct
|
||||
editor_edit_format: editor-diff
|
||||
pass_rate_1: 9.8
|
||||
pass_rate_2: 26.2
|
||||
pass_num_1: 22
|
||||
pass_num_2: 59
|
||||
percent_cases_well_formed: 100.0
|
||||
error_outputs: 122
|
||||
num_malformed_responses: 0
|
||||
num_with_malformed_responses: 0
|
||||
user_asks: 489
|
||||
lazy_comments: 8
|
||||
syntax_errors: 0
|
||||
indentation_errors: 0
|
||||
exhausted_context_windows: 1
|
||||
test_timeouts: 2
|
||||
total_tests: 225
|
||||
command: aider --model fireworks_ai/accounts/fireworks/models/qwq-32b --architect
|
||||
date: 2025-03-07
|
||||
versions: 0.75.3.dev
|
||||
seconds_per_case: 137.4
|
||||
total_cost: 0
|
|
@ -71,7 +71,7 @@ The model also has to successfully apply all its changes to the source file with
|
|||
<script>
|
||||
{% assign data_source = edit_sorted %}
|
||||
{% assign pass_rate_field = "pass_rate_2" %}
|
||||
{% assign highlight_model = "xxxxxxxxxxx" %}
|
||||
{% assign highlight_model = "xxxxxx" %}
|
||||
{% include leaderboard.js %}
|
||||
</script>
|
||||
<style>
|
||||
|
|
Loading…
Add table
Add a link
Reference in a new issue