GLM-5 vs Nemotron 3.5 Super VL 120B A12B
Change modelsGLM-5Z.AI
IndexAll categories, out of 100.
50.8 ±3.6 best
50.6 ±5.0
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
90% best
85%
SpeedOutput tokens per second.
43/s
—
EloLMArena rating and rank.
1446
—
ReleasedMonth of release.
2026-02
2026-10
Input / 1MUS dollars per 1M input tokens.
$1.00
—
Output / 1MUS dollars per 1M output tokens.
$3.20
—
1K chats2K tokens in, 500 out, each.
$3.60
—
1K documents20K tokens in, 1K out, each.
$23.20
—
1K agent tasks200K tokens in, 20K out, each.
$264.00
—
ContextMaximum tokens in one request.
205K
1M best
AgenticMulti-step tasks with tools.
50.4 best
47.9
CodingCode writing and repair.
52.8 best
52.3
ReasoningLogic problems and puzzles.
47.8
55.2 best
MultimodalTasks with images and text.
—
47.2
KnowledgeFacts and expert knowledge.
51.6
52.8 best
MultilingualTasks in many languages.
52.1
—
InstructionTasks with strict prompt rules.
52.4
54.5 best
MathMath problems.
51.7
—
Benchmarks
11 sharedOnly GLM-5: 52Only Nemotron 3.5 Super VL 120B A12B: 18
GLM-5
Nemotron 3.5 Super VL 120B A12B