Claude 3.7 Sonnet Thinking vs Granite 4.2 30B
Change modelsClaude 3.7 Sonnet ThinkingAnthropic
IndexAll categories, out of 100.
41.4 ±4.7
41.6 ±5.4 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
—
1361
ReleasedMonth of release.
2025-02
2026-08
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
200K best
128K
AgenticMulti-step tasks with tools.
39.1
42.0 best
CodingCode writing and repair.
39.5
43.2 best
ReasoningLogic problems and puzzles.
38.6
39.2 best
MultimodalTasks with images and text.
48.1
—
KnowledgeFacts and expert knowledge.
44.1 best
35.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
42.5
61.1 best
MathMath problems.
36.6
47.5 best
Benchmarks
5 sharedOnly Claude 3.7 Sonnet Thinking: 19Only Granite 4.2 30B: 15
Claude 3.7 Sonnet Thinking
Granite 4.2 30B