improved over time plot

This commit is contained in:
Paul Gauthier 2024-11-20 20:16:25 -08:00
parent c797af020a
commit 8302e9d0dd
4 changed files with 540 additions and 976 deletions

View file

@ -1,7 +1,7 @@
- dirname: 2024-05-01-20-05-59--direct-opus-filenames-outside-fence
test_cases: 133
model: claude-3-opus-20240229
released: 2024-02-29
_released: 2024-02-29
edit_format: diff
commit_hash: f4b1797-dirty, f4b1797
pass_rate_1: 53.4
@ -623,7 +623,7 @@
commit_hash: d31eef3-dirty
pass_rate_1: 40.6
pass_rate_2: 55.6
released: 2024-07-18
_released: 2024-07-18
percent_cases_well_formed: 100.0
error_outputs: 1
num_malformed_responses: 0
@ -691,7 +691,7 @@
- dirname: 2024-07-24-06-30-29--llama-405b-whole
test_cases: 133
model: llama-3.1-405b-instruct (whole)
released: 2024-07-23
_released: 2024-07-23
edit_format: whole
commit_hash: a362dea-dirty
pass_rate_1: 48.9