Claude Haiku 4.5 Thinking vs Trinity-Large-Thinking
Change modelsClaude Haiku 4.5 ThinkingAnthropic
Trinity-Large-ThinkingArcee AI
IndexAll categories, out of 100.
43.5 ±7.0
43.5 ±7.2
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
75%
75%
SpeedOutput tokens per second.
—
138/s
EloLMArena rating and rank.
—
1340
ReleasedMonth of release.
2025-10
2026-03
Input / 1MUS dollars per 1M input tokens.
—
$0.25
Output / 1MUS dollars per 1M output tokens.
—
$0.80
1K chats2K tokens in, 500 out, each.
—
$0.90
1K documents20K tokens in, 1K out, each.
—
$5.80
1K agent tasks200K tokens in, 20K out, each.
—
$66.00
ContextMaximum tokens in one request.
200K
262K best
AgenticMulti-step tasks with tools.
50.2 best
44.0
CodingCode writing and repair.
42.5
48.3 best
ReasoningLogic problems and puzzles.
—
36.0
MultimodalTasks with images and text.
30.1
—
KnowledgeFacts and expert knowledge.
43.6
45.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
39.8
MathMath problems.
51.6
—
Benchmarks
3 sharedOnly Claude Haiku 4.5 Thinking: 25Only Trinity-Large-Thinking: 15
Claude Haiku 4.5 Thinking
Trinity-Large-Thinking