Claude Sonnet 5 vs Gemini 3.5 Flash

Change models
IndexAll categories, out of 100.
64.2 ±2.7
64.2 ±2.8
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
75/s
137/s best
EloLMArena rating and rank.
1442
1483 best
ReleasedMonth of release.
2026-06
2026-05
Input / 1MUS dollars per 1M input tokens.
$2.00
$1.50 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$9.00 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
$4.50 best
1K chats2K tokens in, 500 out, each.
$9.00
$7.50 best
1K documents20K tokens in, 1K out, each.
$50.00
$39.00 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$480.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
65.3 best
64.7
CodingCode writing and repair.
65.3 best
60.8
ReasoningLogic problems and puzzles.
66.5 best
62.2
MultimodalTasks with images and text.
59.6
64.7 best
KnowledgeFacts and expert knowledge.
59.0
68.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
55.8
69.9 best
MathMath problems.
64.8 best
61.5

Benchmarks

56 shared
Only Claude Sonnet 5: 30Only Gemini 3.5 Flash: 35
Claude Sonnet 5
Gemini 3.5 Flash
41.3%41 / 222
42.7% best36 / 222
82.0% best29 / 217
69.3%115 / 217
80.3%88 / 217
92.8% best24 / 217
16.9% best43 / 214
13.1%55 / 214
80.0%86 / 200
95.6% best40 / 200
91.1%27 / 199
92.2% best21 / 199
40.1%51 / 164
51.9% best15 / 164
83.9% best45 / 149
83.6%51 / 149
TaxEval v2Finance
75.6% best14 / 143
74.4%36 / 143
82.4%52 / 142
87.6% best12 / 142
88.9%32 / 135
92.7% best14 / 135
MMLU ProKnowledge
87.5%26 / 135
89.5% best10 / 135
48.2% best29 / 133
42.2%45 / 133
CorpFin v2Finance
67.0% best13 / 131
64.7%34 / 131
81.3% best29 / 123
48.7%68 / 123
54.3% best34 / 114
53.9%37 / 114
77.3%40 / 113
84.3% best8 / 113
MedScribeHealthcare
76.1%77 / 109
76.6% best75 / 109
MedCodeHealthcare
47.5%33 / 106
55.8% best6 / 106
70.0% best4 / 97
68.1%19 / 97