Tencent Hy4 Coding Benchmark
How Tencent Hy4 ranks on the LLM Coding Leaderboard, shown next to the three models directly above and below it, with the top three models included for reference.
Last evaluated: 16 hours ago (November 6, 2026), with OpenCode.
| # | Model | Total points (max 70) |
Avg cost per prompt |
Avg time per prompt |
Video | Tested with | Points per project | Consistency penalty | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
|
Laravel Code Quality
(max 20) |
React-TS Code Quality
(max 20) |
Bug Finding Test
(max 10) |
Edge-case Testing (4 projects, max 20) |
||||||||
| 1 | Opus 5.5 (High) | 67.26 | $0.83 | 03:42 |
Claude Code |
18.68 | 19 | 9.58 | 20 | 0 | |
| 2 | GPT-6-Astra (High) | 66.35 | $0.96 | 04:34 |
Codex CLI |
18.6 | 18.17 | 9.58 | 20 | 0 | |
| 3 | GPT-6-Astra (Medium) | 66.03 | $0.69 | 03:08 |
Codex CLI |
18.2 | 17.83 | 10 | 20 | 0 | |
| ⋯ 34 places not shown ⋯ | |||||||||||
| 38 | Mistral Large 4 (High) | 50.31 | $0.18 | 05:30 |
OpenCode |
17.78 | 18.5 | 3.13 | 12.4 | −1.50 | |
| 39 | Tencent Hy3 (High) | 49.37 | $0.05 | 06:35 |
OpenCode |
16.8 | 14.33 | 2.29 | 16.45 | −0.50 | |
| 40 | Deepseek-V4-Pro-0813 (Max) | 49.35 | $0.05 | 09:06 |
OpenCode |
17.3 | 16.5 | 4.9 | 11.65 | −1.00 | |
| 41 | Tencent Hy4 (High) | 48.31 | $0.45 | 16:32 |
OpenCode |
18.05 | 16.83 | 4.58 | 10.65 | −1.80 | |
| 42 | Deepseek-V4-Pro-0813 (High) | 47.34 | $0.04 | 07:15 |
OpenCode |
17.25 | 16.33 | 2.71 | 12.05 | −1.00 | |
| 43 | Gemini-3.8-Flash (High) | 46.09 | N/A | 02:56 |
Antigravity |
14.8 | 16.67 | 5.42 | 10.2 | −1.00 | |
| 44 | Qwen 3.8 27B (Xhigh) | 45.26 | $0.45 | 23:22 |
OpenCode |
17.23 | 15.67 | 2.71 | 12.15 | −2.50 | |
How to read this
- Each score measures a model-and-harness configuration, not the model in isolation.
- Prices are calculated with API costs. Models tested on a subscription plan show N/A.
- Full methodology and scoring formulas are explained in this article.
See every tested model side by side on the full LLM Coding Leaderboard.
