Claude Opus 5.5 vs GPT-5.4 Pro
Change modelsClaude Opus 5.5Anthropic
GPT-5.4 ProOpenAI
IndexAll categories, out of 100.
78.6 ±2.4 best
73.3 ±8.7
GapIndex points below the top.
Top
−5.3 · no clear gap
CoverageIndex weight that has results.
95% best
60%
SpeedOutput tokens per second.
76/s best
21/s
EloLMArena rating and rank.
1513
—
ReleasedMonth of release.
2026-09
2026-03
Input / 1MUS dollars per 1M input tokens.
$4.00 best
$30.00
Output / 1MUS dollars per 1M output tokens.
$20.00 best
$180.00
Batch output / 1MBatch price per 1M output tokens.
$10.00 best
$90.00
1K chats2K tokens in, 500 out, each.
$18.00 best
$150.00
1K documents20K tokens in, 1K out, each.
$100.00 best
$780.00
1K agent tasks200K tokens in, 20K out, each.
$1,200.00 best
$9,600.00
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
74.1 best
70.5
CodingCode writing and repair.
81.8
—
ReasoningLogic problems and puzzles.
80.8 best
80.4
MultimodalTasks with images and text.
74.1
—
KnowledgeFacts and expert knowledge.
79.2 best
67.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
59.6
—
MathMath problems.
77.7 best
75.3
Benchmarks
11 sharedOnly Claude Opus 5.5: 146Only GPT-5.4 Pro: 7
Claude Opus 5.5
GPT-5.4 Pro