GPT-6.2 Sol vs GPT-6 Sol

Change models
GPT-6 SolOpenAI
IndexAll categories, out of 100.
76.0 ±4.6 best
71.2 ±2.2
GapIndex points below the top.
Top
−4.8 · no clear gap
CoverageIndex weight that has results.
85%
100% best
SpeedOutput tokens per second.
56/s
81/s best
EloLMArena rating and rank.
1414 best
1398
ReleasedMonth of release.
2026-11
2026-09
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.
72.9 best
67.3
CodingCode writing and repair.
78.6 best
72.2
ReasoningLogic problems and puzzles.
78.8 best
74.2
MultimodalTasks with images and text.
73.2 best
69.1
KnowledgeFacts and expert knowledge.
75.7 best
70.5
MultilingualTasks in many languages.
71.9 best
65.2
InstructionTasks with strict prompt rules.
—
64.3
MathMath problems.
—
74.3

Benchmarks

34 shared
Only GPT-6.2 Sol: 14Only GPT-6 Sol: 60
GPT-6.2 Sol
GPT-6 Sol
EuroEval PolishMultilingual
66.2% best5 / 227
62.4%16 / 227
EuroEval SwedishMultilingual
77.1% best4 / 213
71.3%8 / 213
EuroEval GermanMultilingual
66.8% best5 / 208
63.1%8 / 208
74.0% best5 / 199
70.1%8 / 199
EuroEval FrenchMultilingual
75.7% best5 / 195
70.4%11 / 195
EuroEval SpanishMultilingual
69.0% best3 / 194
65.6%9 / 194
EuroEval DutchMultilingual
73.4% best4 / 192
67.5%9 / 192
EuroEval ItalianMultilingual
77.4% best4 / 191
69.9%10 / 191
61.6% best7 / 170
54.5%16 / 170
85.8%15 / 137
89.6% best12 / 137
97.5% best7 / 132
95.5%20 / 132
87.6%16 / 130
87.8% best14 / 130
91.7% best15 / 127
90.0%20 / 127
98.1% best12 / 116
97.8%16 / 116
37.0% best52 / 98
28.8%64 / 98
24.8% best49 / 89
15.0%68 / 89
60.6% best7 / 68
44.4%18 / 68
13.4 best10 / 59
9.314 / 59
10.9 best12 / 59
3.919 / 59
18.0% best3 / 55
7.0%17 / 55