GPT-5.4 Pro vs GPT-5.6 Sol

Change models
IndexAll categories, out of 100.
73.3 ±8.7 best
73.0 ±1.9
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
60%
100% best
SpeedOutput tokens per second.
21/s
64/s best
EloLMArena rating and rank.
—
1457
ReleasedMonth of release.
2026-03
2026-07
Input / 1MUS dollars per 1M input tokens.
$30.00
$4.40 best
Output / 1MUS dollars per 1M output tokens.
$180.00
$22.00 best
Batch output / 1MBatch price per 1M output tokens.
$90.00
$10.00 best
1K chats2K tokens in, 500 out, each.
$150.00
$19.80 best
1K documents20K tokens in, 1K out, each.
$780.00
$110.00 best
1K agent tasks200K tokens in, 20K out, each.
$9,600.00
$1,320.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
70.5
71.9 best
CodingCode writing and repair.
—
70.4
ReasoningLogic problems and puzzles.
80.4 best
76.3
MultimodalTasks with images and text.
—
72.6
KnowledgeFacts and expert knowledge.
67.2
72.7 best
MultilingualTasks in many languages.
—
66.4
InstructionTasks with strict prompt rules.
—
64.5
MathMath problems.
75.3 best
75.1

Benchmarks

11 shared
Only GPT-5.4 Pro: 7Only GPT-5.6 Sol: 114
GPT-5.4 Pro
GPT-5.6 Sol
94.6% best8 / 217
93.5%17 / 217
30.0%10 / 214
32.3% best3 / 214
83.3%19 / 131
92.5% best3 / 131
94.5%21 / 126
96.5% best11 / 126
92.2%12 / 122
93.8% best10 / 122
98.3%8 / 116
99.0% best2 / 116
46.3%40 / 91
69.7% best10 / 91
Chess PuzzlesReasoning
59.0%10 / 90
59.0%10 / 90
82.5%17 / 90
89.1% best9 / 90
58.5%20 / 72
82.9% best10 / 72
BrowseCompAgentic
89.3%11 / 63
92.2% best2 / 63