Claude Opus 4.7 vs GPT-5.3 Codex
Change modelsClaude Opus 4.7Anthropic
GPT-5.3 CodexOpenAI
IndexAll categories, out of 100.
62.0 ±3.0
62.0 ±5.3
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
47/s
52/s best
EloLMArena rating and rank.
1483
—
ReleasedMonth of release.
2026-04
2026-02
Input / 1MUS dollars per 1M input tokens.
$5.00
$1.75 best
Output / 1MUS dollars per 1M output tokens.
$25.00
$14.00 best
Batch output / 1MBatch price per 1M output tokens.
$12.50
—
1K chats2K tokens in, 500 out, each.
$22.50
$10.50 best
1K documents20K tokens in, 1K out, each.
$125.00
$49.00 best
1K agent tasks200K tokens in, 20K out, each.
$1,500.00
$630.00 best
ContextMaximum tokens in one request.
1M best
400K
AgenticMulti-step tasks with tools.
60.6
60.6
CodingCode writing and repair.
64.5 best
61.8
ReasoningLogic problems and puzzles.
61.1
67.0 best
MultimodalTasks with images and text.
61.3 best
57.3
KnowledgeFacts and expert knowledge.
61.8
64.1 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
45.7
59.5 best
MathMath problems.
64.3
—
Benchmarks
14 sharedOnly Claude Opus 4.7: 51Only GPT-5.3 Codex: 7
Claude Opus 4.7
GPT-5.3 Codex