Claude Opus 5 vs GPT-6.2 Sol

Change models
Claude Opus 5Anthropic
IndexAll categories, out of 100.
72.1 ±1.9
76.0 ±4.6 best
GapIndex points below the top.
−3.9 · no clear gap
Top
CoverageIndex weight that has results.
100% best
85%
SpeedOutput tokens per second.
68/s best
56/s
EloLMArena rating and rank.
1502 best
1414
ReleasedMonth of release.
2026-07
2026-11
Input / 1MUS dollars per 1M input tokens.
$5.00
$2.00 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$10.00 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
$5.00 best
1K chats2K tokens in, 500 out, each.
$22.50
$9.00 best
1K documents20K tokens in, 1K out, each.
$125.00
$50.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$600.00 best
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
70.1
72.9 best
CodingCode writing and repair.
73.4
78.6 best
ReasoningLogic problems and puzzles.
73.5
78.8 best
MultimodalTasks with images and text.
67.1
73.2 best
KnowledgeFacts and expert knowledge.
73.0
75.7 best
MultilingualTasks in many languages.
62.3
71.9 best
InstructionTasks with strict prompt rules.
55.1
—
MathMath problems.
73.3
—

Benchmarks

24 shared
Only Claude Opus 5: 127Only GPT-6.2 Sol: 24
Claude Opus 5
GPT-6.2 Sol
60.9%9 / 170
61.6% best7 / 170
90.4% best10 / 137
85.8%15 / 137
97.5%7 / 132
97.5%7 / 132
88.4% best13 / 130
87.6%16 / 130
97.1% best8 / 127
91.7%15 / 127
99.0% best3 / 116
98.1%12 / 116
55.3% best3 / 98
37.0%52 / 98
47.1% best7 / 89
24.8%49 / 89
53.5%14 / 68
60.6% best7 / 68
2.422 / 59
13.4 best10 / 59
10.114 / 59
10.9 best12 / 59
12.0%13 / 55
18.0% best3 / 55
52.1%15 / 52
61.5% best7 / 52
27.1%13 / 48
58.6% best4 / 48
79.3% best6 / 34
77.8%9 / 34
37.4% best10 / 34
36.9%11 / 34
28.1%17 / 32
43.8% best6 / 32
30.2%8 / 30
54.9% best5 / 30
27.0%20 / 30
54.7% best5 / 30
53.8%6 / 26
53.8%6 / 26