GPT-5.5 vs GPT-5.6 Sol

Change models
GPT-5.5OpenAI
IndexAll categories, out of 100.
69.1 ±2.5
73.0 ±1.9 best
GapIndex points below the top.
−3.9
Top
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
52/s
64/s best
EloLMArena rating and rank.
1466 best
1457
ReleasedMonth of release.
2026-04
2026-07
Input / 1MUS dollars per 1M input tokens.
$5.00
$4.40 best
Output / 1MUS dollars per 1M output tokens.
$30.00
$22.00 best
Batch output / 1MBatch price per 1M output tokens.
$15.00
$10.00 best
1K chats2K tokens in, 500 out, each.
$25.00
$19.80 best
1K documents20K tokens in, 1K out, each.
$130.00
$110.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,600.00
$1,320.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.8
71.9 best
CodingCode writing and repair.
65.5
70.4 best
ReasoningLogic problems and puzzles.
74.1
76.3 best
MultimodalTasks with images and text.
66.8
72.6 best
KnowledgeFacts and expert knowledge.
70.4
72.7 best
MultilingualTasks in many languages.
—
66.4
InstructionTasks with strict prompt rules.
64.8 best
64.5
MathMath problems.
74.7
75.1 best

Benchmarks

88 shared
Only GPT-5.5: 24Only GPT-5.6 Sol: 37
GPT-5.5
GPT-5.6 Sol
45.8%26 / 222
49.5% best13 / 222
84.3% best7 / 217
84.0%8 / 217
94.0% best13 / 217
93.5%17 / 217
27.1%17 / 214
32.3% best3 / 214
100.0%1 / 200
100.0%1 / 200
93.5%8 / 199
94.1% best5 / 199
58.0%10 / 164
59.4% best8 / 164
86.5%13 / 149
87.0% best7 / 149
98.0% best8 / 149
85.1%56 / 149
75.9% best16 / 146
72.7%34 / 146
TaxEval v2Finance
75.0% best25 / 143
74.8%29 / 143
85.3% best33 / 142
82.6%51 / 142
93.6%8 / 141
94.6% best4 / 141
93.2%10 / 135
95.2% best2 / 135
MMLU ProKnowledge
88.1%21 / 135
89.1% best15 / 135
42.5%44 / 133
55.4% best19 / 133
85.0%13 / 131
92.5% best3 / 131
CorpFin v2Finance
68.4% best9 / 131
64.4%37 / 131
95.0%19 / 126
96.5% best11 / 126
69.8%50 / 123
80.5% best31 / 123