GLM-4.7 vs GLM-5
Change models
IndexAll categories, out of 100.
50.0 ±4.6
51.6 ±3.6 best
GapIndex points below the top.
−1.6 · no clear gap
Top
CoverageIndex weight that has results.
85%
90% best
SpeedOutput tokens per second.
28/s
45/s best
EloLMArena rating and rank.
1435
1446 best
ReleasedMonth of release.
2025-12
2026-02
Input / 1MUS dollars per 1M input tokens.
$0.60 best
$1.00
Output / 1MUS dollars per 1M output tokens.
$2.20 best
$3.20
1K chats2K tokens in, 500 out, each.
$2.30 best
$3.60
1K documents20K tokens in, 1K out, each.
$14.20 best
$23.20
1K agent tasks200K tokens in, 20K out, each.
$164.00 best
$264.00
ContextMaximum tokens in one request.
205K
205K
AgenticMulti-step tasks with tools.
48.8
51.6 best
CodingCode writing and repair.
53.2
53.5 best
ReasoningLogic problems and puzzles.
48.7 best
48.3
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
50.9
51.8 best
MultilingualTasks in many languages.
—
52.5
InstructionTasks with strict prompt rules.
52.5
53.1 best
MathMath problems.
49.1
52.5 best
Benchmarks
20 sharedOnly GLM-4.7: 26Only GLM-5: 43
GLM-4.7
GLM-5