GLM-4.5 vs GLM-4.6
Change models
IndexAll categories, out of 100.
45.7 ±9.2 best
41.8 ±5.4
GapIndex points below the top.
Top
−3.9 · no clear gap
CoverageIndex weight that has results.
65%
85% best
SpeedOutput tokens per second.
25/s
30/s best
EloLMArena rating and rank.
1430
1440 best
ReleasedMonth of release.
2025-07
2025-09
Input / 1MUS dollars per 1M input tokens.
$0.60
$0.50 best
Output / 1MUS dollars per 1M output tokens.
$2.20
$2.00 best
1K chats2K tokens in, 500 out, each.
$2.30
$2.00 best
1K documents20K tokens in, 1K out, each.
$14.20
$12.00 best
1K agent tasks200K tokens in, 20K out, each.
$164.00
$140.00 best
ContextMaximum tokens in one request.
131K
205K best
AgenticMulti-step tasks with tools.
48.1
48.8 best
CodingCode writing and repair.
43.3
46.7 best
ReasoningLogic problems and puzzles.
—
31.1
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
45.1 best
39.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
23.3
MathMath problems.
48.4 best
44.9
Benchmarks
15 sharedOnly GLM-4.5: 1Only GLM-4.6: 12
GLM-4.5
GLM-4.6