mirror of
https://github.com/Aider-AI/aider.git
synced 2025-05-29 16:54:59 +00:00
Updated plot dimensions and axis labels for better visualization in benchmark over time.
This commit is contained in:
parent
d05de029e1
commit
445c73267a
2 changed files with 5 additions and 6 deletions
|
@ -343,7 +343,6 @@
|
||||||
- dirname: 2024-05-07-12-55-06--deepseek-chat-v2-whole
|
- dirname: 2024-05-07-12-55-06--deepseek-chat-v2-whole
|
||||||
test_cases: 133
|
test_cases: 133
|
||||||
model: deepseek-chat v2 (whole)
|
model: deepseek-chat v2 (whole)
|
||||||
released: 2024-05-06
|
|
||||||
edit_format: whole
|
edit_format: whole
|
||||||
commit_hash: b1cae73, db994fb
|
commit_hash: b1cae73, db994fb
|
||||||
pass_rate_1: 50.4
|
pass_rate_1: 50.4
|
||||||
|
|
|
@ -23,22 +23,22 @@ def plot_over_time(yaml_file):
|
||||||
|
|
||||||
rc("font", **{"family": "sans-serif", "sans-serif": ["Helvetica"], "size": 10})
|
rc("font", **{"family": "sans-serif", "sans-serif": ["Helvetica"], "size": 10})
|
||||||
|
|
||||||
fig, ax = plt.subplots(figsize=(10, 4))
|
fig, ax = plt.subplots(figsize=(10, 5))
|
||||||
ax.grid(axis="y", zorder=0, lw=0.2)
|
ax.grid(axis="y", zorder=0, lw=0.2)
|
||||||
for spine in ax.spines.values():
|
for spine in ax.spines.values():
|
||||||
spine.set_edgecolor('#DDDDDD')
|
spine.set_edgecolor('#DDDDDD')
|
||||||
spine.set_linewidth(0.5)
|
spine.set_linewidth(0.5)
|
||||||
|
|
||||||
colors = ['red' if 'gpt-4' in model else 'green' if 'gpt-3.5' in model else 'blue' for model in models]
|
colors = ['red' if 'gpt-4' in model else 'green' if 'gpt-3.5' in model else 'blue' for model in models]
|
||||||
ax.scatter(dates, pass_rates, c=colors, alpha=0.5, s=100)
|
ax.scatter(dates, pass_rates, c=colors, alpha=0.5, s=120)
|
||||||
|
|
||||||
for i, model in enumerate(models):
|
for i, model in enumerate(models):
|
||||||
ax.annotate(model, (dates[i], pass_rates[i]), fontsize=12, alpha=0.75,
|
ax.annotate(model, (dates[i], pass_rates[i]), fontsize=12, alpha=0.75,
|
||||||
xytext=(5, 5), textcoords='offset points')
|
xytext=(5, 5), textcoords='offset points')
|
||||||
|
|
||||||
ax.set_xlabel('Model release date', fontsize=14)
|
ax.set_xlabel('Model release date', fontsize=18)
|
||||||
ax.set_ylabel('Aider code editing benchmark,\npercent completed correctly', fontsize=14)
|
ax.set_ylabel('Aider code editing benchmark,\npercent completed correctly', fontsize=18)
|
||||||
ax.set_title('LLM code editing skill by model release date')
|
ax.set_title('LLM code editing skill by model release date', fontsize=20)
|
||||||
plt.tight_layout()
|
plt.tight_layout()
|
||||||
plt.savefig("tmp_over_time.png")
|
plt.savefig("tmp_over_time.png")
|
||||||
imgcat(fig)
|
imgcat(fig)
|
||||||
|
|
Loading…
Add table
Add a link
Reference in a new issue