Claude Sonnet 4 Thinking vs Gemini 2.5 Pro
Change modelsClaude Sonnet 4 ThinkingAnthropic
Gemini 2.5 ProGoogle
IndexAll categories, out of 100.
46.9 ±8.2 best
46.6 ±4.1
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
75%
95% best
SpeedOutput tokens per second.
—
91/s
EloLMArena rating and rank.
—
1458
ReleasedMonth of release.
—
2025-03
Input / 1MUS dollars per 1M input tokens.
—
$1.25
Output / 1MUS dollars per 1M output tokens.
—
$10.00
Batch output / 1MBatch price per 1M output tokens.
—
$5.00
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.
—
1.05M
AgenticMulti-step tasks with tools.
50.8 best
40.4
CodingCode writing and repair.
41.8
48.8 best
ReasoningLogic problems and puzzles.
—
48.3
MultimodalTasks with images and text.
52.7 best
52.6
KnowledgeFacts and expert knowledge.
48.1
53.0 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
34.5
MathMath problems.
46.0
46.0
Benchmarks
6 sharedOnly Claude Sonnet 4 Thinking: 10Only Gemini 2.5 Pro: 27
Claude Sonnet 4 Thinking
Gemini 2.5 Pro