Gemini 4 Hydrogen Coding Benchmark
How Gemini 4 Hydrogen 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. Gemini 4 Hydrogen was tested at 2 effort levels, each ranked separately.
Last evaluated: 3 days ago (November 13, 2026), with Antigravity.
| # | Model | Total points (max 90) |
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) |
Python Code Quality
(max 20) |
Edge-case Testing (4 projects, max 20) |
||||||||
| 1 | Opus 5.5 (High) | 84.95 | $0.83 | 03:42 |
Claude Code |
18.68 | 19 | 9.1 | 18.17 | 20 | 0 | |
| 2 | Fable 5.2 (Medium) | 84.7 | $1.42 | 03:03 |
Claude Code |
19.13 | 19.5 | 9.52 | 17.8 | 18.75 | 0 | |
| 3 | GPT-6-Astra (High) | 84.25 | $0.96 | 04:34 |
Codex CLI |
18.6 | 18.17 | 9.03 | 18.47 | 20 | −0.02 | |
| ⋯ 5 places not shown ⋯ | ||||||||||||
| 9 | Kimi K3.1 Pro (Max) | 79.85 | $0.74 | 13:39 |
OpenCode |
18.55 | 18.33 | 8.75 | 16.47 | 17.75 | 0 | |
| 10 | GPT-6.1-Sol (Low) | 78.8 | $0.10 | 01:21 |
Codex CLI |
17.53 | 16.67 | 8.75 | 18.1 | 18.5 | −0.75 | |
| 11 | Opus 5.5 (Low) | 78.19 | $0.37 | 01:21 |
Claude Code |
17.37 | 18.17 | 6.63 | 18.1 | 18.5 | −0.58 | |
| 12 | Gemini 4 Hydrogen (High) | 78.01 | N/A | 03:42 |
Antigravity |
18.23 | 17.33 | 7.92 | 16.27 | 18.75 | −0.49 | |
| 13 | GPT-6.1-Terra (Max) | 77.67 | $0.27 | 07:55 |
Codex CLI |
17.82 | 18.17 | 8.61 | 16.7 | 16.5 | −0.13 | |
| 14 | Deepseek-V4.1-Flash-1017 (Max) | 77.08 | $0.07 | 07:09 |
OpenCode |
17.42 | 18.17 | 8.47 | 16.27 | 17.25 | −0.50 | |
| 15 | Deepseek-V4.1-Flash-1017 (Max) | 76.99 | N/A | 04:58 |
DeepSeek Harness |
18.07 | 18.67 | 8.75 | 16.5 | 15.5 | −0.50 | |
| ⋯ 2 places not shown ⋯ | ||||||||||||
| 18 | Kimi K3.1 Pro (High) | 75.47 | $0.25 | 05:23 |
OpenCode |
17.7 | 17.33 | 7.36 | 17.8 | 17.25 | −1.97 | |
| 19 | Sonnet 5.5 (Medium) | 75.44 | $0.20 | 00:58 |
Claude Code |
17.88 | 18.33 | 6.18 | 16.63 | 17.25 | −0.83 | |
| 20 | Grok 4.7 (High) | 75.44 | $1.85 | 23:27 |
Cursor |
17.7 | 18.33 | 8.06 | 15.6 | 16.25 | −0.50 | |
| 21 | Gemini 4 Hydrogen (Medium) | 73.44 | N/A | 01:43 |
Antigravity |
17.35 | 16.17 | 6.18 | 17.27 | 16.75 | −0.28 | |
| 22 | GPT-6-Luna (Max) | 73.06 | $0.03 | 11:03 |
Codex CLI |
18.12 | 17.17 | 7.08 | 16.03 | 16.7 | −2.04 | |
| 23 | Gemini 4 Argon (High) | 72.46 | N/A | 09:41 |
Devin |
17.15 | 18.5 | 7.64 | 15.17 | 14.25 | −0.25 | |
| 24 | SWE-2 (Max) | 72.45 | N/A | 11:59 |
Devin |
17.5 | 17.83 | 6.67 | 16.73 | 14.45 | −0.73 | |
Videos about Gemini 4 Hydrogen
I Tested NEW Gemini 4 Hydrogen on Coding: It's a GAME-CHANGER
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.