Gemini 3.8 Flash vs Gemini 4 Argon

Change models
IndexAll categories, out of 100.
67.8 ±2.5
78.5 ±4.3 best
GapIndex points below the top.
−10.7
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
68/s best
28/s
EloLMArena rating and rank.
1500
1530 best
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.825 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$4.13 best
$10.00
Batch output / 1MBatch price per 1M output tokens.
$1.88 best
$5.00
1K chats2K tokens in, 500 out, each.
$3.71 best
$9.00
1K documents20K tokens in, 1K out, each.
$20.63 best
$50.00
1K agent tasks200K tokens in, 20K out, each.
$247.50 best
$600.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.3
77.3 best
CodingCode writing and repair.
66.2
76.7 best
ReasoningLogic problems and puzzles.
68.3
79.8 best
MultimodalTasks with images and text.
67.1
—
KnowledgeFacts and expert knowledge.
70.9
76.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
91.3
—
MathMath problems.
64.3
75.9 best

Benchmarks

68 shared
Only Gemini 3.8 Flash: 38Only Gemini 4 Argon: 18
Gemini 3.8 Flash
Gemini 4 Argon
47.8%20 / 222
57.1% best4 / 222
81.3% best34 / 217
79.7%45 / 217
95.4%5 / 217
96.4% best2 / 217
18.3%34 / 214
27.1% best17 / 214
98.9%22 / 200
100.0% best1 / 200
50.5% best19 / 164
48.3%26 / 164
87.0%7 / 149
88.3% best3 / 149
46.8%34 / 133
56.2% best14 / 133
89.2%11 / 131
91.3% best7 / 131
98.5%1 / 126
98.5%1 / 126
78.7%34 / 123
91.9% best3 / 123
92.5%11 / 122
97.1% best6 / 122
98.0%11 / 116
99.5% best1 / 116
56.6%23 / 114
61.8% best5 / 114
MedScribeHealthcare
84.5%34 / 109
87.4% best17 / 109
MedCodeHealthcare
48.1%31 / 106
58.8% best3 / 106
69.7%10 / 91
76.0% best3 / 91
Chess PuzzlesReasoning
58.0%14 / 90
59.0% best10 / 90
68.4%32 / 90
86.0% best13 / 90
38.9%38 / 90
54.8% best5 / 90