Claude Opus 5 vs Gemini 3.8 Flash

Change models
Claude Opus 5Anthropic
IndexAll categories, out of 100.
73.8 ±1.9 best
67.8 ±2.5
GapIndex points below the top.
Top
−6.0
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
48/s
68/s best
EloLMArena rating and rank.
1502 best
1500
ReleasedMonth of release.
2026-07
2026-09
Input / 1MUS dollars per 1M input tokens.
$5.00
$0.825 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$4.13 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
$1.88 best
1K chats2K tokens in, 500 out, each.
$22.50
$3.71 best
1K documents20K tokens in, 1K out, each.
$125.00
$20.63 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$247.50 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
71.6 best
65.3
CodingCode writing and repair.
74.8 best
66.2
ReasoningLogic problems and puzzles.
75.4 best
68.3
MultimodalTasks with images and text.
72.5 best
67.1
KnowledgeFacts and expert knowledge.
73.1 best
70.9
MultilingualTasks in many languages.
63.6
—
InstructionTasks with strict prompt rules.
55.6
91.3 best
MathMath problems.
74.8 best
64.3

Benchmarks

87 shared
Only Claude Opus 5: 63Only Gemini 3.8 Flash: 19
Claude Opus 5
Gemini 3.8 Flash
54.9% best7 / 222
47.8%20 / 222
79.3%52 / 217
81.3% best34 / 217
93.9%14 / 217
95.4% best5 / 217
29.1% best13 / 214
18.3%34 / 214
98.9%22 / 200
98.9%22 / 200
93.2%11 / 199
95.3% best2 / 199
60.9% best7 / 164
50.5%19 / 164
87.0%7 / 149
87.0%7 / 149
TaxEval v2Finance
75.1% best23 / 143
74.4%36 / 143
89.0%4 / 142
89.5% best3 / 142
93.4%7 / 135
94.4% best4 / 135
MMLU ProKnowledge
91.6% best2 / 135
90.2%5 / 135
61.1% best7 / 133
46.8%34 / 133
90.4% best8 / 131
89.2%11 / 131
97.5%5 / 126
98.5% best1 / 126
88.4% best11 / 123
78.7%34 / 123
97.1% best6 / 122
92.5%11 / 122
99.0% best2 / 116
98.0%11 / 116
56.4%26 / 114
56.6% best23 / 114
84.7%6 / 113
85.6% best4 / 113