Inference
EN

Gemini 4 Argon vs Hy4

Change models
Gemini 4 ArgonGoogle
Hy4Tencent
IndexAll categories, out of 100.
78.5 ±4.3 best
72.0 ±7.8
GapIndex points below the top.
Top
−6.5 · no clear gap
CoverageIndex weight that has results.
80% best
65%
SpeedOutput tokens per second.
28/s
52/s best
EloLMArena rating and rank.
1530
—
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.417 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$1.25 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$9.00
$1.46 best
1K documents20K tokens in, 1K out, each.
$50.00
$9.59 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$108.41 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
77.3 best
74.5
CodingCode writing and repair.
76.7 best
68.4
ReasoningLogic problems and puzzles.
79.8
—
MultimodalTasks with images and text.
—
57.4
KnowledgeFacts and expert knowledge.
76.5
83.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
75.9
—

Benchmarks

11 shared
Only Gemini 4 Argon: 75Only Hy4: 10
Gemini 4 Argon
Hy4
Vibe Code Bench v1.1Coding
91.9% best3 / 123
81.0%30 / 123
Legal Research BenchLegal
54.8% best5 / 90
41.3%30 / 90
Tax Agent BenchFinance
49.2% best4 / 82
34.4%17 / 82
Terminal-Bench 4.0Agentic
57.6% best8 / 61
39.4%15 / 61
DeepSWEAgentic
77.9% best3 / 59
74.9%8 / 59
Agent Arena steerabilityAgentic
13.2 best9 / 54
8.814 / 54
Agent Arena task outcomeAgentic
13.2 best7 / 54
6.712 / 54
HLAB-Vals-1.1Legal
27.1% best1 / 35
12.5%17 / 35
AutomationBenchAgentic
51.3%12 / 32
56.2% best4 / 32
FrontierCode 2.0Coding
26.3%14 / 27
31.0% best9 / 27
Agents' Last ExamAgentic
39.5%9 / 21
41.0% best8 / 21