Claude Opus 4.6 vs Gemini 3 Pro

Change models
IndexAll categories, out of 100.
58.0 ±3.0 best
57.9 ±2.7
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
36/s
109/s best
EloLMArena rating and rank.
1497 best
1480
ReleasedMonth of release.
2026-02
2025-11
Input / 1MUS dollars per 1M input tokens.
$5.00
$2.00 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$12.00 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
—
1K chats2K tokens in, 500 out, each.
$22.50
$10.00 best
1K documents20K tokens in, 1K out, each.
$125.00
$52.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$640.00 best
ContextMaximum tokens in one request.
1M
2M best
AgenticMulti-step tasks with tools.
57.8 best
56.2
CodingCode writing and repair.
59.2 best
56.4
ReasoningLogic problems and puzzles.
55.3
57.2 best
MultimodalTasks with images and text.
52.6
54.8 best
KnowledgeFacts and expert knowledge.
61.8
66.1 best
MultilingualTasks in many languages.
—
60.1
InstructionTasks with strict prompt rules.
30.7
54.8 best
MathMath problems.
63.8 best
58.2

Benchmarks

26 shared
Only Claude Opus 4.6: 38Only Gemini 3 Pro: 49
Claude Opus 4.6
Gemini 3 Pro
19.1%116 / 222
39.7% best48 / 222
67.0%130 / 217
76.0% best88 / 217
88.4%54 / 217
92.6% best27 / 217
2.8%101 / 214
9.1% best70 / 214
91.1%58 / 200
91.4% best56 / 200
84.0%86 / 199
90.8% best30 / 199
45.8%34 / 164
55.8% best11 / 164
84.8%58 / 149
87.1% best48 / 149
44.6%87 / 146
70.4% best42 / 146
57.6% best61 / 123
14.3%99 / 123
72.5%69 / 113
80.2% best22 / 113
MedScribeHealthcare
86.7% best21 / 109
72.0%91 / 109
MedCodeHealthcare
48.2%30 / 106
52.2% best14 / 106
40.7% best7 / 69
37.6%12 / 69
75.6% best5 / 65
69.6%17 / 65
90.0% best2 / 64
80.0%6 / 64
22.9% best8 / 55
18.8%10 / 55
77.3%29 / 53
81.0% best12 / 53
61.9%10 / 52
63.2% best7 / 52
0.0%3 / 36
0.0%3 / 36