List your company

Code Generation on LiveCode (Pass@1)

42.8Pass@1Qwen 3.5
-0.8810.4621.833.14Feb 4, 2026Feb 20, 2026Mar 8, 2026Mar 24, 2026Apr 9, 2026Apr 25, 2026May 11, 2026

Evaluation results

MethodLinks
Qwen 3.5Zero-shot=true, Parameters=122B-A10B, Organization=Alibaba Cloud2026.0542.8
Nemotron 3 SuperZero-shot=true, Parameters=120B-A12B, Organization=Nvidia2026.0541.26
GLM-4.5VZero-shot=true, Parameters=106B-A12B, Organization=Z.ai2026.0534.15
Phoenix-VL 1.5 MediumZero-shot=true, Parameters=123B, Organization=HTX2026.0532.4
Llama 4 MaverickZero-shot=true, Parameters=400B-A17B, Organization=MetaAI2026.0526.46
GRIP 16BModel Size=16B, Total Budget=300B tokens2026.026.4
GRIP 8BModel Size=8B, Total Budget=300B tokens2026.025.3
6. GRIP (Full)Model=GRIP-8B, Total Budget=100B tokens2026.022.9
5. + DiversityModel=GRIP-8B, Total Budget=100B tokens2026.022.5
4. + Loss ReplayModel=GRIP-8B, Total Budget=100B tokens2026.022.4
3. + Static ReplayModel=GRIP-8B, Total Budget=100B tokens2026.021.8
Random 16BModel Size=16B, Total Budget=300B tokens2026.021.5
2. + Static BudgetModel=GRIP-8B, Total Budget=100B tokens2026.021.3
Random 8BModel Size=8B, Total Budget=300B tokens2026.021.2
1. RandomModel=GRIP-8B, Total Budget=100B tokens2026.020.8