Gemini 4 Carbon vs GPT-6.2 Sol

Change models
IndexAll categories, out of 100.
80.5 ±3.7 best
76.0 ±4.6
GapIndex points below the top.
Top
−4.5 · no clear gap
CoverageIndex weight that has results.
90% best
85%
SpeedOutput tokens per second.
55/s
56/s best
EloLMArena rating and rank.
1539 best
1414
ReleasedMonth of release.
2026-10
2026-11
Input / 1MUS dollars per 1M input tokens.
$2.00
$2.00
Output / 1MUS dollars per 1M output tokens.
$10.00
$10.00
Batch output / 1MBatch price per 1M output tokens.
$5.00
$5.00
1K chats2K tokens in, 500 out, each.
$9.00
$9.00
1K documents20K tokens in, 1K out, each.
$50.00
$50.00
1K agent tasks200K tokens in, 20K out, each.
$600.00
$600.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
81.1 best
72.9
CodingCode writing and repair.
79.5 best
78.6
ReasoningLogic problems and puzzles.
79.2 best
78.8
MultimodalTasks with images and text.
82.8 best
73.2
KnowledgeFacts and expert knowledge.
78.1 best
75.7
MultilingualTasks in many languages.
—
71.9
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
75.5
—

Benchmarks

22 shared
Only Gemini 4 Carbon: 24Only GPT-6.2 Sol: 26
Gemini 4 Carbon
GPT-6.2 Sol
58.3%12 / 170
61.6% best7 / 170
92.1% best7 / 137
85.8%15 / 137
97.5%7 / 132
97.5%7 / 132
89.1% best11 / 130
87.6%16 / 130
97.9% best3 / 127
91.7%15 / 127
98.5% best7 / 116
98.1%12 / 116
55.8% best2 / 98
37.0%52 / 98
51.8% best3 / 89
24.8%49 / 89
63.1% best4 / 68
60.6%7 / 68
17.9 best4 / 59
13.410 / 59
17.2 best5 / 59
10.912 / 59
16.0%8 / 55
18.0% best3 / 55
64.5% best4 / 52
61.5%7 / 52
17.5% best10 / 42
12.1%21 / 42
42.6%7 / 32
43.8% best6 / 32
63.9% best3 / 30
54.9%5 / 30
57.3% best4 / 30
54.7%5 / 30
77.8% best2 / 24
71.3%10 / 24
19.4%18 / 24
37.2% best6 / 24
28.4%7 / 23
30.0% best4 / 23