GLM-5.1 vs GLM-5V-Turbo

Change models
IndexAll categories, out of 100.
56.0 ±4.1 best
48.1 ±8.6
GapIndex points below the top.
Top
−7.9 · no clear gap
CoverageIndex weight that has results.
85% best
65%
SpeedOutput tokens per second.
102/s best
30/s
EloLMArena rating and rank.
1463 best
1438
ReleasedMonth of release.
2026-04
2026-04
Input / 1MUS dollars per 1M input tokens.
$1.40
$1.20 best
Output / 1MUS dollars per 1M output tokens.
$4.40
$4.00 best
1K chats2K tokens in, 500 out, each.
$5.00
$4.40 best
1K documents20K tokens in, 1K out, each.
$32.40
$28.00 best
1K agent tasks200K tokens in, 20K out, each.
$368.00
$320.00 best
ContextMaximum tokens in one request.
205K best
203K
AgenticMulti-step tasks with tools.
59.2 best
50.5
CodingCode writing and repair.
57.0
—
ReasoningLogic problems and puzzles.
50.9 best
46.8
MultimodalTasks with images and text.
—
49.9
KnowledgeFacts and expert knowledge.
51.7 best
46.9
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
60.3 best
46.1
MathMath problems.
54.9
—

Benchmarks

9 shared
Only GLM-5.1: 51Only GLM-5V-Turbo: 1
GLM-5.1
GLM-5V-Turbo
30.1% best79 / 222
17.1%121 / 222
73.7% best100 / 217
70.3%112 / 217
4.6% best87 / 214
0.6%132 / 214
86.8% best61 / 199
80.9%97 / 199
23.7%111 / 164
29.3% best80 / 164
97.7%9 / 149
98.5% best3 / 149
76.3% best13 / 146
61.1%62 / 146
60.1% best12 / 52
30.8%48 / 52
Claw-EvalAgentic
62.3% best24 / 42
53.8%36 / 42