GLM-5V-Turbo vs K-EXAONE 2.0

Change models
K-EXAONE 2.0LG AI Research
IndexAll categories, out of 100.
48.6 ±8.6 best
48.3 ±5.4
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
65%
85% best
SpeedOutput tokens per second.
27/s
—
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-04
2026-07
Input / 1MUS dollars per 1M input tokens.
$1.20
—
Output / 1MUS dollars per 1M output tokens.
$4.00
—
1K chats2K tokens in, 500 out, each.
$4.40
—
1K documents20K tokens in, 1K out, each.
$28.00
—
1K agent tasks200K tokens in, 20K out, each.
$320.00
—
ContextMaximum tokens in one request.
203K
262K best
AgenticMulti-step tasks with tools.
52.8
55.4 best
CodingCode writing and repair.
—
49.1
ReasoningLogic problems and puzzles.
46.2 best
41.9
MultimodalTasks with images and text.
49.4
—
KnowledgeFacts and expert knowledge.
47.0 best
43.9
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
45.7
52.3 best
MathMath problems.
—
50.2

Benchmarks

6 shared
Only GLM-5V-Turbo: 4Only K-EXAONE 2.0: 15
GLM-5V-Turbo
K-EXAONE 2.0
17.1%117 / 216
18.6% best116 / 216
70.3% best107 / 211
56.2%139 / 211
0.6%127 / 207
0.9% best119 / 207
80.9%93 / 193
82.9% best85 / 193
29.3% best82 / 170
14.5%160 / 170
Claw-EvalAgentic
53.8%36 / 42
77.7% best3 / 42