List your company

Software Engineering on SWE-bench verified (All)

93.8Success RateACE
48.24860.07471.983.726Apr 28, 2026

Evaluation results

MethodLinks
ACERepo=scikit-learn, N=32, Base Model=GPT-5.42026.0493.8451
TF-GRPORepo=scikit-learn, N=32, Base Model=GPT-5.42026.0493.8378
NexAU0Repo=scikit-learn, N=32, Base Model=GPT-5.42026.0493.8307
AHERepo=scikit-learn, N=32, Base Model=GPT-5.42026.0487.5257
AHERepo=django, N=231, Base Model=GPT-5.42026.0481484
ACERepo=django, N=231, Base Model=GPT-5.42026.0479.2707
NexAU0Repo=django, N=231, Base Model=GPT-5.42026.0479.2527
TF-GRPORepo=django, N=231, Base Model=GPT-5.42026.0478.8583
ACERepo=pydata, N=22, Base Model=GPT-5.42026.0477.3563
TF-GRPORepo=pydata, N=22, Base Model=GPT-5.42026.0477.3516
NexAU0Repo=pydata, N=22, Base Model=GPT-5.42026.0477.3386
AHERepo=All, N=500, Base Model=GPT-5.4, Evolution Source=terminal-bench-long-time2026.0475.6461
NexAU0Repo=All, N=500, Base Model=GPT-5.4, Self-evolution loop=None (Seed)2026.0475.2526
ACERepo=All, N=500, Base Model=GPT-5.4, Evolution Source=terminal-bench-long-time2026.0474.6679
TF-GRPORepo=All, N=500, Base Model=GPT-5.4, Evolution Source=terminal-bench-long-time2026.0474.2582
NexAU0Repo=matplotlib, N=34, Base Model=GPT-5.42026.0473.5486
AHERepo=matplotlib, N=34, Base Model=GPT-5.42026.0473.5391
AHERepo=pydata, N=22, Base Model=GPT-5.42026.0472.7338
NexAU0Repo=sympy, N=75, Base Model=GPT-5.42026.0470.7494
AHERepo=sympy, N=75, Base Model=GPT-5.42026.0470.7479
ACERepo=matplotlib, N=34, Base Model=GPT-5.42026.0470.6622
TF-GRPORepo=matplotlib, N=34, Base Model=GPT-5.42026.0470.6530
AHERepo=sphinx-doc, N=44, Base Model=GPT-5.42026.0470.5656
ACERepo=sympy, N=75, Base Model=GPT-5.42026.0469.3602
NexAU0Repo=sphinx-doc, N=44, Base Model=GPT-5.42026.0468.2731
TF-GRPORepo=sympy, N=75, Base Model=GPT-5.42026.0468572
TF-GRPORepo=sphinx-doc, N=44, Base Model=GPT-5.42026.0465.9848
ACERepo=sphinx-doc, N=44, Base Model=GPT-5.42026.0461.4990
ACERepo=astropy, N=22, Base Model=GPT-5.42026.0459.1546
TF-GRPORepo=astropy, N=22, Base Model=GPT-5.42026.0459.1470
NexAU0Repo=astropy, N=22, Base Model=GPT-5.42026.0454.5667
AHERepo=astropy, N=22, Base Model=GPT-5.42026.0450277