mirror of
https://github.com/Aider-AI/aider.git
synced 2025-06-01 10:14:59 +00:00
update models-over-time
This commit is contained in:
parent
0a3c6bfbe7
commit
1ced72b728
2 changed files with 722 additions and 235 deletions
|
@ -577,6 +577,7 @@
|
||||||
pass_rate_2: 77.4
|
pass_rate_2: 77.4
|
||||||
percent_cases_well_formed: 99.2
|
percent_cases_well_formed: 99.2
|
||||||
error_outputs: 23
|
error_outputs: 23
|
||||||
|
released: 2024-06-20
|
||||||
num_malformed_responses: 4
|
num_malformed_responses: 4
|
||||||
num_with_malformed_responses: 1
|
num_with_malformed_responses: 1
|
||||||
user_asks: 2
|
user_asks: 2
|
||||||
|
@ -603,6 +604,7 @@
|
||||||
num_malformed_responses: 0
|
num_malformed_responses: 0
|
||||||
num_with_malformed_responses: 0
|
num_with_malformed_responses: 0
|
||||||
user_asks: 0
|
user_asks: 0
|
||||||
|
released: 2024-03-13
|
||||||
lazy_comments: 0
|
lazy_comments: 0
|
||||||
syntax_errors: 0
|
syntax_errors: 0
|
||||||
indentation_errors: 0
|
indentation_errors: 0
|
||||||
|
@ -644,6 +646,7 @@
|
||||||
commit_hash: d31eef3-dirty
|
commit_hash: d31eef3-dirty
|
||||||
pass_rate_1: 40.6
|
pass_rate_1: 40.6
|
||||||
pass_rate_2: 55.6
|
pass_rate_2: 55.6
|
||||||
|
released: 2024-07-18
|
||||||
percent_cases_well_formed: 100.0
|
percent_cases_well_formed: 100.0
|
||||||
error_outputs: 1
|
error_outputs: 1
|
||||||
num_malformed_responses: 0
|
num_malformed_responses: 0
|
||||||
|
@ -668,6 +671,7 @@
|
||||||
pass_rate_1: 60.9
|
pass_rate_1: 60.9
|
||||||
pass_rate_2: 69.9
|
pass_rate_2: 69.9
|
||||||
percent_cases_well_formed: 97.7
|
percent_cases_well_formed: 97.7
|
||||||
|
released: 2024-06-28
|
||||||
error_outputs: 58
|
error_outputs: 58
|
||||||
num_malformed_responses: 13
|
num_malformed_responses: 13
|
||||||
num_with_malformed_responses: 3
|
num_with_malformed_responses: 3
|
||||||
|
@ -690,6 +694,7 @@
|
||||||
commit_hash: f7ce78b-dirty
|
commit_hash: f7ce78b-dirty
|
||||||
pass_rate_1: 46.6
|
pass_rate_1: 46.6
|
||||||
pass_rate_2: 63.9
|
pass_rate_2: 63.9
|
||||||
|
released: 2024-07-23
|
||||||
percent_cases_well_formed: 92.5
|
percent_cases_well_formed: 92.5
|
||||||
error_outputs: 84
|
error_outputs: 84
|
||||||
num_malformed_responses: 19
|
num_malformed_responses: 19
|
||||||
|
@ -716,6 +721,7 @@
|
||||||
percent_cases_well_formed: 100.0
|
percent_cases_well_formed: 100.0
|
||||||
error_outputs: 0
|
error_outputs: 0
|
||||||
num_malformed_responses: 0
|
num_malformed_responses: 0
|
||||||
|
released: 2024-07-23
|
||||||
num_with_malformed_responses: 0
|
num_with_malformed_responses: 0
|
||||||
user_asks: 0
|
user_asks: 0
|
||||||
lazy_comments: 0
|
lazy_comments: 0
|
||||||
|
@ -738,6 +744,7 @@
|
||||||
pass_rate_2: 72.9
|
pass_rate_2: 72.9
|
||||||
percent_cases_well_formed: 97.7
|
percent_cases_well_formed: 97.7
|
||||||
error_outputs: 13
|
error_outputs: 13
|
||||||
|
released: 2024-07-24
|
||||||
num_malformed_responses: 3
|
num_malformed_responses: 3
|
||||||
num_with_malformed_responses: 3
|
num_with_malformed_responses: 3
|
||||||
user_asks: 1
|
user_asks: 1
|
||||||
|
@ -763,6 +770,7 @@
|
||||||
error_outputs: 3
|
error_outputs: 3
|
||||||
num_malformed_responses: 0
|
num_malformed_responses: 0
|
||||||
num_with_malformed_responses: 0
|
num_with_malformed_responses: 0
|
||||||
|
released: 2024-07-24
|
||||||
user_asks: 3
|
user_asks: 3
|
||||||
lazy_comments: 0
|
lazy_comments: 0
|
||||||
syntax_errors: 1
|
syntax_errors: 1
|
||||||
|
@ -785,6 +793,7 @@
|
||||||
percent_cases_well_formed: 100.0
|
percent_cases_well_formed: 100.0
|
||||||
error_outputs: 27
|
error_outputs: 27
|
||||||
num_malformed_responses: 0
|
num_malformed_responses: 0
|
||||||
|
released: 2024-07-23
|
||||||
num_with_malformed_responses: 0
|
num_with_malformed_responses: 0
|
||||||
user_asks: 23
|
user_asks: 23
|
||||||
lazy_comments: 8
|
lazy_comments: 8
|
||||||
|
@ -810,6 +819,7 @@
|
||||||
num_malformed_responses: 0
|
num_malformed_responses: 0
|
||||||
num_with_malformed_responses: 0
|
num_with_malformed_responses: 0
|
||||||
user_asks: 0
|
user_asks: 0
|
||||||
|
released: 2024-07-23
|
||||||
lazy_comments: 0
|
lazy_comments: 0
|
||||||
syntax_errors: 0
|
syntax_errors: 0
|
||||||
indentation_errors: 0
|
indentation_errors: 0
|
||||||
|
@ -838,6 +848,7 @@
|
||||||
indentation_errors: 2
|
indentation_errors: 2
|
||||||
exhausted_context_windows: 0
|
exhausted_context_windows: 0
|
||||||
test_timeouts: 5
|
test_timeouts: 5
|
||||||
|
released: 2024-08-06
|
||||||
command: aider --model openai/gpt-4o-2024-08-06
|
command: aider --model openai/gpt-4o-2024-08-06
|
||||||
date: 2024-08-06
|
date: 2024-08-06
|
||||||
versions: 0.48.1-dev
|
versions: 0.48.1-dev
|
||||||
|
@ -863,6 +874,7 @@
|
||||||
test_timeouts: 0
|
test_timeouts: 0
|
||||||
command: aider --model openai/chatgpt-4o-latest
|
command: aider --model openai/chatgpt-4o-latest
|
||||||
date: 2024-08-14
|
date: 2024-08-14
|
||||||
|
released: 2024-08-08
|
||||||
versions: 0.50.2-dev
|
versions: 0.50.2-dev
|
||||||
seconds_per_case: 26.3
|
seconds_per_case: 26.3
|
||||||
total_cost: 3.6113
|
total_cost: 3.6113
|
||||||
|
|
File diff suppressed because it is too large
Load diff
Before Width: | Height: | Size: 53 KiB After Width: | Height: | Size: 74 KiB |
Loading…
Add table
Add a link
Reference in a new issue