added draft article

This commit is contained in:
Paul Gauthier 2024-05-31 09:33:31 -07:00
parent a168daf5fc
commit 0120d434ff
5 changed files with 2433 additions and 2 deletions

7
benchmark/swe-bench.txt Normal file
View file

@ -0,0 +1,7 @@
18.8% Aider|GPT-4o|& Opus|(570)
17.0% Aider|GPT-4o|(570)
13.9% Devin|(570)
13.8% Amazon Q|Developer|Agent|(2294)
12.5% SWE-|Agent|+ GPT-4|(2294)
10.6% AutoCode|Rover|(2294)
10.5% SWE-|Agent|+ Opus|(2294)

View file

@ -52,7 +52,7 @@ def plot_swe_bench_lite(data_file):
for model, bar in zip(models, bars):
yval = bar.get_height()
y = yval - 1.25
y = yval - 1
va = "top"
color = "#eee" if "Aider" in model else "#555"
fontfamily = "Helvetica Bold" if "Aider" in model else "Helvetica"
@ -76,7 +76,7 @@ def plot_swe_bench_lite(data_file):
ax.set_title(title, fontsize=20)
# ax.set_ylim(0, 29.9)
plt.xticks(
fontsize=16,
fontsize=17,
color=font_color,
)