Playground · Gemini 4 Hydrogen model page

Gemini 4 Hydrogen in the playground

2 tests; our pick in 0. Each answer is linked to the test, where it runs live beside the other models'.

Our pick: 0 of 2 tests
Checks passed: 93% 6.5 of 7
All checks passed: 1 of 2 tests
Rank: 6 of 24 models by checks passed
Cost: $0.60 every try; $0.11 for the answers shown
Time: 6.8 min every try; 102 s for the answers shown
Tries: 3 for 2 answers; 1 needed more than one
Thinking: 15% of its output tokens

Every test Gemini 4 Hydrogen took. Choose Checks, Cost, Time or Thinking to sort.
Test	Our notes	Checks	Time	Cost	Thinking
Make a stained glass window of a hummingbird and flowers Animation · 13 models	An arched window. It draws the cartoon as dashed lines, cuts the border pieces first and then the rest one by one, darkens the lead lines and lights the glass, all in about 12 seconds. The sun follows the pointer, and the panes nearest it brighten. A click starts it again. The picture is the weak part: the hummingbird has a clear head, eye and long beak, but its body and tail are a jumble of blue and purple shards, the flowers are blocky red and green shapes, and a large patch in the middle of the window is never glazed. At its default settings the first try hit the 65,536-token output limit after five minutes ($0.49), with half of that spent thinking, and never finished the page; we asked again at low reasoning and that answer is shown: 56 seconds and $0.065, or 6 minutes and $0.56 for both.Took 2 tries: ran out of room at 943,718 tokens; finished at 943,718 tokens, low thinking.	3.5 of 4	56 s 6.0 min over 2 tries	$0.065 $0.556 over 2 tries	14%
Pelican riding a bicycle Drawing · 22 models	A white pelican with a crest, a yellow eye and a long beak over a shaded orange pouch, on a red bicycle on a pale road under clouds. It sits on the saddle with a long wing stretched to the grip, the near foot flat on a pedal and the far leg running to the other crank. The bicycle is complete, with spoked wheels, a chainring and a chain, though the bird is drawn stiffly side-on. Close to Gemini 4 Carbon's on the checks, with less going on around it. 1 try, 46 seconds, $0.045.	3 of 3	46 s	$0.045	18%

Time and cost are for the answer shown; when it took more than one try, the second line counts every try, and sorting uses every try. Thinking is the share of the answer's output tokens spent reasoning before it wrote.

Tries

1 answer needed more than one try

We ask again when an answer runs out of room, comes back empty, stops mid-page or sends no code: first as it was, then with twice the room, then with thinking off. Each try below, in order.

Test	Try	What happened	Limit	Output tokens	Time	Cost
Make a stained glass window of a hummingbird and flowers	1 of 2	Ran out of room	943,718	65,536 33,837 thinking	5.1 min	$0.492
Make a stained glass window of a hummingbird and flowers	2 of 2	Finished, low thinking	943,718	8,602 1,167 thinking	56 s	$0.065

Against the other models

Checks passed on each test

All models →

Gemini 4 Hydrogen's column is marked.

Share of checks passed by each model on each test; a star marks our pick.
Test	Claude Fable 5.2	Claude Fable 5.1	Kimi K3	GPT-6.1 Sol	Kimi K3.1 Pro	Gemini 4 Hydrogen	Claude Opus 5.5	DeepSeek V4.1 Flash 1017	Muse Spark 1.3	DeepSeek V4.1 Flash	Gemini 4 Carbon	GPT-6 Luna	Claude Haiku 5.5	Muse Wonder Full	GPT-6.1 Terra	Mercury 3	Mistral Large 4	Grok 4.7	MiniMax M3.1 Flash (free route)	Qwen3.8 Max (0902)	Gemini 3.8 Flash	Muse Wonder	Gemini 4 Argon	Muse Ember
Make a stained glass window of a hummingbird and flowers	4/4Claude Fable 5.2: 4 of 4 checks	–Claude Fable 5.1: did not take this test	–Kimi K3: did not take this test	–GPT-6.1 Sol: did not take this test	3.5/4Kimi K3.1 Pro: 3.5 of 4 checks	3.5/4Gemini 4 Hydrogen: 3.5 of 4 checks	4/4Claude Opus 5.5: 4 of 4 checks, our pick	3.5/4DeepSeek V4.1 Flash 1017: 3.5 of 4 checks	–Muse Spark 1.3: did not take this test	–DeepSeek V4.1 Flash: did not take this test	4/4Gemini 4 Carbon: 4 of 4 checks	–GPT-6 Luna: did not take this test	–Claude Haiku 5.5: did not take this test	3.5/4Muse Wonder Full: 3.5 of 4 checks	3.5/4GPT-6.1 Terra: 3.5 of 4 checks	3.5/4Mercury 3: 3.5 of 4 checks	–Mistral Large 4: did not take this test	–Grok 4.7: did not take this test	3/4MiniMax M3.1 Flash (free route): 3 of 4 checks	–Qwen3.8 Max (0902): did not take this test	–Gemini 3.8 Flash: did not take this test	2.5/4Muse Wonder: 2.5 of 4 checks	·Gemini 4 Argon: not checked	·Muse Ember: not checked
Pelican riding a bicycle	3/3Claude Fable 5.2: 3 of 3 checks	3/3Claude Fable 5.1: 3 of 3 checks	3/3Kimi K3: 3 of 3 checks	3/3GPT-6.1 Sol: 3 of 3 checks, our pick	3/3Kimi K3.1 Pro: 3 of 3 checks	3/3Gemini 4 Hydrogen: 3 of 3 checks	3/3Claude Opus 5.5: 3 of 3 checks	3/3DeepSeek V4.1 Flash 1017: 3 of 3 checks	3/3Muse Spark 1.3: 3 of 3 checks	2/3DeepSeek V4.1 Flash: 2 of 3 checks	3/3Gemini 4 Carbon: 3 of 3 checks	2.5/3GPT-6 Luna: 2.5 of 3 checks	2/3Claude Haiku 5.5: 2 of 3 checks	–Muse Wonder Full: did not take this test	2.5/3GPT-6.1 Terra: 2.5 of 3 checks	3/3Mercury 3: 3 of 3 checks	3/3Mistral Large 4: 3 of 3 checks	2/3Grok 4.7: 2 of 3 checks	2.5/3MiniMax M3.1 Flash (free route): 2.5 of 3 checks	3/3Qwen3.8 Max (0902): 3 of 3 checks	2.5/3Gemini 3.8 Flash: 2.5 of 3 checks	–Muse Wonder: did not take this test	·Gemini 4 Argon: not checked	·Muse Ember: not checked