Sign in

Is Hy4 SOTA in Coding?#16 in CodingRanked #16 in Coding.

How it scores here

Hy4 in Coding

Primary benchmarks

  • Terminal-Bench 4.0: 39.1 (CI 35.6–42.6) on Nov 18, 2026 (#16 of 44).

On the category's weighted score it is 33.2 points behind #1 Claude Sonnet 5.5 and 0.3 behind the next model up, DeepSeek V4.1 Flash. At $0.625 per 1M tokens, 3 of 47 priced models rank higher in Coding for the same price or less.

Nearby on the board

#ModelCategory score
13Muse Wonder Full69.2
14DeepSeek V4.1 Flash 101768.9
15DeepSeek V4.1 Flash65.4
16Hy465.1
17Claude Haiku 5.563.9
18Grok 4.761.5
19GPT-5.6 Sol60.5
Standings

Coding

#ModelState
1Claude Sonnet 5.5Co-SOTA
1Claude Opus 5.5Co-SOTA
1Kimi K3.1 ProCo-SOTA
2Claude Fable 5.2Near-SOTA
3GPT-6 AstraNear-SOTA
4GPT-6.1 Sol#4 in this category
5Claude Fable 5.1#5 in this category
6Claude Opus 5#6 in this category
7Gemini 4 Argon#7 in this category
8GPT-6.1 Terra#8 in this category
9GPT-6 Sol#9 in this category
10Muse Wonder#10 in this category

Category page →