From 9b88f8caf62a21eb3933caccfa9948d8bd5e6f97 Mon Sep 17 00:00:00 2001 From: Paul Gauthier Date: Sat, 4 May 2024 07:59:27 -0700 Subject: [PATCH] updated gpt-4-0314 --- _data/leaderboard.csv | 2 +- benchmark/benchmark.py | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/_data/leaderboard.csv b/_data/leaderboard.csv index bbb158a1e..b4525fd32 100644 --- a/_data/leaderboard.csv +++ b/_data/leaderboard.csv @@ -9,7 +9,7 @@ gpt-3.5-turbo-0301,57.9,50.4,whole,aider --model gpt-3.5-turbo-0301,0.16.4-dev,4 gpt-3.5-turbo-0613,50.4,38.3,whole,aider --model gpt-3.5-turbo-0613,0.16.4-dev,93aa497-dirty,11/7/23 gpt-3.5-turbo-1106,56.1,45.5,whole,aider --model gpt-3.5-turbo-1106,0.30.1,7b14d77,4/30/24 gpt-4-0125-preview,66.2,55.6,udiff,aider --model gpt-4-0125-preview,0.22.1-dev,edcf9b1,1/25/24 -gpt-4-0314,68.4,51.1,diff,aider --model gpt-4-0314,0.7.2,506bfe2 c7c548d,7/1/23 +gpt-4-0314,62.4,51.1,diff,aider --model gpt-4-0314,0.31.2-dev,c9dbca9 f6580ff-dirty,5/4/24 gpt-4-0613,67.7,46.6,diff,aider -4,0.18.1,3aa17c4,12/16/23 gpt-4-1106-preview,63.2,57.1,udiff,aider,0.31.2-dev,1981105-dirty,5/4/24 gpt-4-turbo-2024-04-09,64.4,49.2,diff,aider --gpt-4-turbo,0.30.1,e610e5b,5/1/24 diff --git a/benchmark/benchmark.py b/benchmark/benchmark.py index 2b6f453d2..35314b370 100755 --- a/benchmark/benchmark.py +++ b/benchmark/benchmark.py @@ -878,7 +878,8 @@ def summarize_results(dirname): csv.append(f"{first:.1f}") csv.append(" ".join(variants["edit_format"])) - csv.append("aider") + model = variants["model"].pop() + csv.append(f"aider --model {model}") versions = set() for hsh in variants["commit_hash"]: if not hsh: