DeepSeek V4.1 Flash 1017 vs Gemini 4 Argon

Change models
IndexAll categories, out of 100.
68.5 ±2.6
78.5 ±4.3 best
GapIndex points below the top.
−10.0
Top
CoverageIndex weight that has results.
95% best
80%
SpeedOutput tokens per second.
261/s best
28/s
EloLMArena rating and rank.
1463
1530 best
ReleasedMonth of release.
2026-10
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.022 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$10.00
Batch output / 1MBatch price per 1M output tokens.
$0.20 best
$5.00
1K chats2K tokens in, 500 out, each.
$0.244 best
$9.00
1K documents20K tokens in, 1K out, each.
$0.84 best
$50.00
1K agent tasks200K tokens in, 20K out, each.
$12.40 best
$600.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
72.2
77.3 best
CodingCode writing and repair.
69.8
76.7 best
ReasoningLogic problems and puzzles.
65.0
79.8 best
MultimodalTasks with images and text.
62.2
—
KnowledgeFacts and expert knowledge.
64.2
76.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
68.3
—
MathMath problems.
65.4
75.9 best

Benchmarks

64 shared
Only DeepSeek V4.1 Flash 1017: 30Only Gemini 4 Argon: 22
DeepSeek V4.1 Flash 1017
Gemini 4 Argon
39.2%51 / 222
57.1% best4 / 222
84.0% best8 / 217
79.7%45 / 217
89.8%42 / 217
96.4% best2 / 217
14.3%52 / 214
27.1% best17 / 214
98.3%28 / 200
100.0% best1 / 200
46.4%33 / 164
48.3% best26 / 164
83.3%56 / 149
88.3% best3 / 149
55.0%21 / 133
56.2% best14 / 133
72.9%25 / 131
91.3% best7 / 131
94.5%21 / 126
98.5% best1 / 126
84.7%18 / 123
91.9% best3 / 123
81.7%23 / 122
97.1% best6 / 122
98.0%11 / 116
99.5% best1 / 116
51.9%44 / 114
61.8% best5 / 114
MedScribeHealthcare
85.5%27 / 109
87.4% best17 / 109
MedCodeHealthcare
41.2%56 / 106
58.8% best3 / 106
42.9%47 / 91
76.0% best3 / 91
Chess PuzzlesReasoning
48.0%19 / 90
59.0% best10 / 90
67.4%33 / 90
86.0% best13 / 90
41.3%30 / 90
54.8% best5 / 90