GPT-5.4 nano vs GPT-5.5 Pro

Change models
IndexAll categories, out of 100.
50.9 ±2.5
74.8 ±8.7 best
GapIndex points below the top.
−23.9
Top
CoverageIndex weight that has results.
100% best
60%
SpeedOutput tokens per second.
91/s best
19/s
EloLMArena rating and rank.
1372
—
ReleasedMonth of release.
2026-03
2026-04
Input / 1MUS dollars per 1M input tokens.
$0.20 best
$30.00
Output / 1MUS dollars per 1M output tokens.
$1.25 best
$180.00
Batch output / 1MBatch price per 1M output tokens.
$0.625 best
$90.00
1K chats2K tokens in, 500 out, each.
$1.03 best
$150.00
1K documents20K tokens in, 1K out, each.
$5.25 best
$780.00
1K agent tasks200K tokens in, 20K out, each.
$65.00 best
$9,600.00
ContextMaximum tokens in one request.
400K
1.05M best
AgenticMulti-step tasks with tools.
50.5
71.1 best
CodingCode writing and repair.
53.7
—
ReasoningLogic problems and puzzles.
53.7
81.1 best
MultimodalTasks with images and text.
41.7
—
KnowledgeFacts and expert knowledge.
44.5
69.0 best
MultilingualTasks in many languages.
44.4
—
InstructionTasks with strict prompt rules.
61.3
—
MathMath problems.
55.9
76.3 best

Benchmarks

14 shared
Only GPT-5.4 nano: 60Only GPT-5.5 Pro: 1
GPT-5.4 nano
GPT-5.5 Pro
78.5%94 / 217
93.9% best14 / 217
9.3%69 / 214
30.6% best9 / 214
87.8%68 / 200
100.0% best1 / 200
5.7%78 / 131
84.2% best16 / 131
51.5%74 / 126
95.0% best19 / 126
4.2%74 / 122
90.4% best15 / 122
47.9%79 / 116
98.0% best11 / 116
Chess PuzzlesReasoning
45.0%28 / 90
62.0% best8 / 90
44.9%59 / 90
87.7% best11 / 90
37.7%36 / 77
57.2% best11 / 77
12.2%58 / 72
78.0% best12 / 72
25.9%24 / 69
51.0% best2 / 69
6.3%23 / 55
39.6% best2 / 55
24.3%47 / 53
43.1% best23 / 53