Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Code Generation on LiveCodeBench 2408-2505
Loading...
76.43
Pass@1
STEP3-VL-10B (PaCoRe)
47.6012
55.0856
62.57
70.0544
Jan 14, 2026
Pass@1
Score
Updated 3d ago
Evaluation Results
Method
Method
Links
Pass@1
Score
STEP3-VL-10B (PaCoRe)
Reasoning Strategy=PaC...
2026.01
76.43
-
STEP3-VL-10B (SeRe)
Reasoning Strategy=SeR...
2026.01
75.77
-
Gemini-2.5 (Pro)
Model Tier=Pro
2026.01
72.01
-
Qwen3-VL (Thinking)
Thinking Mode=true, Pa...
2026.01
69.45
-
Seed-1.5-VL (Thinking)
Thinking Mode=true
2026.01
57.1
-
GLM-4.6V
Parameters=106B-A12B
2026.01
48.71
-
STEP3-VL-10B
Number of Parameters=10B
2026.01
-
75.77
GLM-4.6V Flash
Number of Parameters=9B
2026.01
-
22.17
Qwen3-VL Thinking
Number of Parameters=8B
2026.01
-
51.05
InternVL 3.5
Number of Parameters=8B
2026.01
-
45.9
MiMo-VL RL-2508
Number of Parameters=7B
2026.01
-
39.65
Feedback
Search any
task
Search any
task