Claude Sonnet 4.5 vs Claude Sonnet 4.5 Thinking
Change modelsClaude Sonnet 4.5Anthropic
Claude Sonnet 4.5 ThinkingAnthropic
IndexAll categories, out of 100.
47.9 ±5.5
53.8 ±6.9 best
GapIndex points below the top.
−5.9 · no clear gap
Top
CoverageIndex weight that has results.
80%
80%
SpeedOutput tokens per second.
45/s
—
EloLMArena rating and rank.
1439
—
ReleasedMonth of release.
2025-09
2025-09
Input / 1MUS dollars per 1M input tokens.
$3.00
—
Output / 1MUS dollars per 1M output tokens.
$15.00
—
Batch output / 1MBatch price per 1M output tokens.
$7.50
—
1K chats2K tokens in, 500 out, each.
$13.50
—
1K documents20K tokens in, 1K out, each.
$75.00
—
1K agent tasks200K tokens in, 20K out, each.
$900.00
—
ContextMaximum tokens in one request.
1M best
200K
AgenticMulti-step tasks with tools.
49.3
57.1 best
CodingCode writing and repair.
53.9 best
50.6
ReasoningLogic problems and puzzles.
45.3
—
MultimodalTasks with images and text.
—
58.4
KnowledgeFacts and expert knowledge.
49.4
53.3 best
MultilingualTasks in many languages.
—
60.4
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
46.6
54.0 best
Benchmarks
3 sharedOnly Claude Sonnet 4.5: 32Only Claude Sonnet 4.5 Thinking: 25
Claude Sonnet 4.5
Claude Sonnet 4.5 Thinking