E-Bench-Code (Internal)

Tencent internal (Hy team) enterprise coding benchmark, reported in the Hy4 preview model card appendix.

Category

Agentic Coding

Max Score

100.0

Score Type

percent

Active

Yes

Model Scores

Scores for E-Bench-Code (Internal)

Model Score Date Verified
Hy3
0.53%
28.08.2026 Verified
Hy4 preview
77.37%
28.08.2026 Verified
DeepSeek V4 Pro
64.30
28.08.2026 Verified
GLM-5.3
11.58%
28.08.2026 Verified
Kimi K3
70.00%
28.08.2026 Verified
GPT-5.6 Sol
100.00%
28.08.2026 Verified
Claude Opus 5
96.84%
28.08.2026 Verified
Qwen3.8-2.4T-A95B
14.74%
28.08.2026 Verified