GPT-5.4 Pro vs GPT-5.5 Pro

Change models
IndexAll categories, out of 100.
73.3 ±8.7
74.8 ±8.7 best
GapIndex points below the top.
−1.5 · no clear gap
Top
CoverageIndex weight that has results.
60%
60%
SpeedOutput tokens per second.
21/s best
19/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-03
2026-04
Input / 1MUS dollars per 1M input tokens.
$30.00
$30.00
Output / 1MUS dollars per 1M output tokens.
$180.00
$180.00
Batch output / 1MBatch price per 1M output tokens.
$90.00
$90.00
1K chats2K tokens in, 500 out, each.
$150.00
$150.00
1K documents20K tokens in, 1K out, each.
$780.00
$780.00
1K agent tasks200K tokens in, 20K out, each.
$9,600.00
$9,600.00
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
70.5
71.1 best
CodingCode writing and repair.
—
—
ReasoningLogic problems and puzzles.
80.4
81.1 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
67.2
69.0 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
75.3
76.3 best

Benchmarks

14 shared
Only GPT-5.4 Pro: 4Only GPT-5.5 Pro: 1
GPT-5.4 Pro
GPT-5.5 Pro
94.6% best8 / 217
93.9%14 / 217
30.0%10 / 214
30.6% best9 / 214
83.3%19 / 131
84.2% best16 / 131
94.5%21 / 126
95.0% best19 / 126
92.2% best12 / 122
90.4%15 / 122
98.3% best8 / 116
98.0%11 / 116
Chess PuzzlesReasoning
59.0%10 / 90
62.0% best8 / 90
82.5%17 / 90
87.7% best11 / 90
58.7% best8 / 77
57.2%11 / 77
58.5%20 / 72
78.0% best12 / 72
50.0%3 / 69
51.0% best2 / 69
BrowseCompAgentic
89.3%11 / 63
90.1% best10 / 63
37.5%3 / 55
39.6% best2 / 55
42.7%25 / 53
43.1% best23 / 53