GLM-5.1 vs GLM-5.2
Change models
IndexAll categories, out of 100.
56.0 ±4.1
60.6 ±3.8 best
GapIndex points below the top.
−4.6 · no clear gap
Top
CoverageIndex weight that has results.
85%
85%
SpeedOutput tokens per second.
102/s
111/s best
EloLMArena rating and rank.
1463
1469 best
ReleasedMonth of release.
2026-04
2026-06
Input / 1MUS dollars per 1M input tokens.
$1.40
<$0.01 best
Output / 1MUS dollars per 1M output tokens.
$4.40 best
$6.80
Batch output / 1MBatch price per 1M output tokens.
—
$0.989
1K chats2K tokens in, 500 out, each.
$5.00
$3.41 best
1K documents20K tokens in, 1K out, each.
$32.40
$6.94 best
1K agent tasks200K tokens in, 20K out, each.
$368.00
$137.40 best
ContextMaximum tokens in one request.
205K
1.05M best
AgenticMulti-step tasks with tools.
59.2
61.7 best
CodingCode writing and repair.
57.0
63.5 best
ReasoningLogic problems and puzzles.
50.9
58.6 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
51.7
55.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
60.3 best
55.1
MathMath problems.
54.9
59.6 best
Benchmarks
43 sharedOnly GLM-5.1: 17Only GLM-5.2: 34
GLM-5.1
GLM-5.2