diff --git a/assets/swe_bench_lite.jpg b/assets/swe_bench_lite.jpg index 9c525c7c4..d7455765e 100644 Binary files a/assets/swe_bench_lite.jpg and b/assets/swe_bench_lite.jpg differ diff --git a/assets/swe_bench_lite.svg b/assets/swe_bench_lite.svg index f5c8faf2d..9affe1f65 100644 --- a/assets/swe_bench_lite.svg +++ b/assets/swe_bench_lite.svg @@ -6,7 +6,7 @@ - 2024-05-23T07:52:54.138893 + 2024-05-23T08:28:16.091496 image/svg+xml @@ -41,12 +41,12 @@ z - - + @@ -453,7 +453,7 @@ z - + @@ -479,7 +479,7 @@ z - + @@ -601,7 +601,7 @@ z - + @@ -674,7 +674,7 @@ z - + @@ -886,7 +886,7 @@ z - + @@ -1007,7 +1007,7 @@ z - + @@ -1043,16 +1043,16 @@ z +" clip-path="url(#p009365f358)" style="fill: none; stroke: #b0b0b0; stroke-width: 0.2; stroke-linecap: square"/> - - + @@ -1087,18 +1087,18 @@ z - + - + - + - + - + - + - + - + - + @@ -1184,18 +1184,18 @@ L 690 158.200121 - + - + - + - + - + - + @@ -1408,62 +1408,62 @@ L 690 50.4 +" clip-path="url(#p009365f358)" style="fill: #b3e6a8; opacity: 0.75"/> +" clip-path="url(#p009365f358)" style="fill: #b3e6a8; opacity: 0.75"/> +" clip-path="url(#p009365f358)" style="fill: #b3d1e6; opacity: 0.75"/> +" clip-path="url(#p009365f358)" style="fill: #b3d1e6; opacity: 0.75"/> +" clip-path="url(#p009365f358)" style="fill: #b3d1e6; opacity: 0.75"/> +" clip-path="url(#p009365f358)" style="fill: #b3d1e6; opacity: 0.75"/> +" clip-path="url(#p009365f358)" style="fill: #b3d1e6; opacity: 0.75"/> - + - + @@ -1556,7 +1556,7 @@ z - + @@ -1566,7 +1566,7 @@ z - + @@ -1576,7 +1576,7 @@ z - + @@ -1586,7 +1586,7 @@ z - + - + + diff --git a/benchmark/swe_bench_lite.py b/benchmark/swe_bench_lite.py index bac10552a..03095689d 100644 --- a/benchmark/swe_bench_lite.py +++ b/benchmark/swe_bench_lite.py @@ -34,14 +34,21 @@ def plot_swe_bench_lite(data_file): colors = ["#b3e6a8" if "Aider" in model else "#b3d1e6" for model in models] bars = ax.bar(models, pass_rates, color=colors, alpha=0.75, zorder=3) - for bar in bars: + for model, bar in zip(models, bars): yval = bar.get_height() + if "Aider" in model: + y = yval + 0.75 + va = "bottom" + else: + y = yval - 1.25 + va = "top" + ax.text( bar.get_x() + bar.get_width() / 2, - yval - 1.25, + y, f"{yval}%", ha="center", - va="top", + va=va, fontsize=14, # alpha=0.75, ) @@ -49,7 +56,7 @@ def plot_swe_bench_lite(data_file): # ax.set_xlabel("Models", fontsize=18) ax.set_ylabel("Instances resolved (%)", fontsize=18, color=font_color) ax.set_title("SWE Bench Lite", fontsize=20) - ax.set_ylim(0, 29) + ax.set_ylim(0, 29.9) plt.xticks( # rotation=45, # ha="center",