GLM-4.6 vs Trinity-Large-Preview
Change modelsGLM-4.6Z.AI
Trinity-Large-PreviewArcee AI
IndexAll categories, out of 100.
41.8 ±5.4
42.2 ±7.6 best
GapIndex points below the top.
−0.4 · no clear gap
Top
CoverageIndex weight that has results.
85% best
75%
SpeedOutput tokens per second.
30/s
—
EloLMArena rating and rank.
1440 best
1339
ReleasedMonth of release.
2025-09
2026-01
Input / 1MUS dollars per 1M input tokens.
$0.50
$0.25 best
Output / 1MUS dollars per 1M output tokens.
$2.00
$1.00 best
1K chats2K tokens in, 500 out, each.
$2.00
$1.00 best
1K documents20K tokens in, 1K out, each.
$12.00
$6.00 best
1K agent tasks200K tokens in, 20K out, each.
$140.00
$70.00 best
ContextMaximum tokens in one request.
205K
512K best
AgenticMulti-step tasks with tools.
48.8 best
48.3
CodingCode writing and repair.
46.7
48.8 best
ReasoningLogic problems and puzzles.
31.1
36.0 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
39.0
39.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
23.3
41.6 best
MathMath problems.
44.9
—
Benchmarks
6 sharedOnly GLM-4.6: 21Only Trinity-Large-Preview: 6
GLM-4.6
Trinity-Large-Preview