Claude Opus 5.5 vs Gemini 3.8 Flash

Change models
IndexAll categories, out of 100.
78.6 ±2.4 best
67.8 ±2.5
GapIndex points below the top.
Top
−10.8
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
76/s best
68/s
EloLMArena rating and rank.
1513 best
1500
ReleasedMonth of release.
2026-09
2026-09
Input / 1MUS dollars per 1M input tokens.
$4.00
$0.825 best
Output / 1MUS dollars per 1M output tokens.
$20.00
$4.13 best
Batch output / 1MBatch price per 1M output tokens.
$10.00
$1.88 best
1K chats2K tokens in, 500 out, each.
$18.00
$3.71 best
1K documents20K tokens in, 1K out, each.
$100.00
$20.63 best
1K agent tasks200K tokens in, 20K out, each.
$1,200.00
$247.50 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
74.1 best
65.3
CodingCode writing and repair.
81.8 best
66.2
ReasoningLogic problems and puzzles.
80.8 best
68.3
MultimodalTasks with images and text.
74.1 best
67.1
KnowledgeFacts and expert knowledge.
79.2 best
70.9
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
59.6
91.3 best
MathMath problems.
77.7 best
64.3

Benchmarks

86 shared
Only Claude Opus 5.5: 71Only Gemini 3.8 Flash: 20
Claude Opus 5.5
Gemini 3.8 Flash
61.4% best2 / 222
47.8%20 / 222
84.7% best6 / 217
81.3%34 / 217
90.6%38 / 217
95.4% best5 / 217
31.7% best4 / 214
18.3%34 / 214
100.0% best1 / 200
98.9%22 / 200
65.5% best3 / 164
50.5%19 / 164
68.3% best1 / 133
46.8%34 / 133
91.7% best6 / 131
89.2%11 / 131
97.5%5 / 126
98.5% best1 / 126
90.3% best6 / 123
78.7%34 / 123
97.9% best3 / 122
92.5%11 / 122
98.3% best8 / 116
98.0%11 / 116
66.9% best2 / 114
56.6%23 / 114
87.7% best1 / 113
85.6%4 / 113
MedScribeHealthcare
91.4% best1 / 109
84.5%34 / 109
MedCodeHealthcare
49.8% best19 / 106
48.1%31 / 106
72.2% best7 / 91
69.7%10 / 91
Chess PuzzlesReasoning
67.0% best5 / 90
58.0%14 / 90
91.2% best4 / 90
68.4%32 / 90
50.5% best7 / 90
38.9%38 / 90