Gemini 4 Neon vs GPT-5.4 Pro

Change models
IndexAll categories, out of 100.
81.9 ±4.4 best
71.8 ±8.7
GapIndex points below the top.
Top
−10.1
CoverageIndex weight that has results.
90% best
60%
SpeedOutput tokens per second.
110/s best
9/s
EloLMArena rating and rank.
1524
—
ReleasedMonth of release.
2026-11
2026-03
Input / 1MUS dollars per 1M input tokens.
$3.00 best
$30.00
Output / 1MUS dollars per 1M output tokens.
$15.00 best
$180.00
Batch output / 1MBatch price per 1M output tokens.
$7.50 best
$90.00
1K chats2K tokens in, 500 out, each.
$13.50 best
$150.00
1K documents20K tokens in, 1K out, each.
$75.00 best
$780.00
1K agent tasks200K tokens in, 20K out, each.
$900.00 best
$9,600.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
81.2 best
69.0
CodingCode writing and repair.
83.5
—
ReasoningLogic problems and puzzles.
87.7 best
78.6
MultimodalTasks with images and text.
72.7
—
KnowledgeFacts and expert knowledge.
78.3 best
66.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
75.9 best
73.7

Benchmarks

5 shared
Only Gemini 4 Neon: 19Only GPT-5.4 Pro: 13
Gemini 4 Neon
GPT-5.4 Pro
96.3% best5 / 220
94.6%12 / 220
75.2% best6 / 94
46.3%43 / 94
Chess PuzzlesReasoning
83.0% best1 / 93
59.0%13 / 93
91.2% best5 / 93
82.5%20 / 93
97.6% best4 / 75
58.5%23 / 75