Claude Sonnet 4.5 Thinking vs GPT-5.1-Codex-Max
Change modelsClaude Sonnet 4.5 ThinkingAnthropic
GPT-5.1-Codex-MaxOpenAI
IndexAll categories, out of 100.
53.8 ±6.9
53.8 ±6.2
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
80%
85% best
SpeedOutput tokens per second.
—
55/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-09
2025-11
Input / 1MUS dollars per 1M input tokens.
—
$1.25
Output / 1MUS dollars per 1M output tokens.
—
$10.00
1K chats2K tokens in, 500 out, each.
—
$7.50
1K documents20K tokens in, 1K out, each.
—
$35.00
1K agent tasks200K tokens in, 20K out, each.
—
$450.00
ContextMaximum tokens in one request.
200K
400K best
AgenticMulti-step tasks with tools.
57.1
57.5 best
CodingCode writing and repair.
50.6
53.2 best
ReasoningLogic problems and puzzles.
—
51.4
MultimodalTasks with images and text.
58.4 best
49.5
KnowledgeFacts and expert knowledge.
53.3
55.7 best
MultilingualTasks in many languages.
60.4
—
InstructionTasks with strict prompt rules.
—
54.4
MathMath problems.
54.0
—
Benchmarks
4 sharedOnly Claude Sonnet 4.5 Thinking: 24Only GPT-5.1-Codex-Max: 8
Claude Sonnet 4.5 Thinking
GPT-5.1-Codex-Max