GLM-5.3 vs Hy4 flash
Change modelsIndexAll categories, out of 100.
65.6 ±3.5 best
65.1 ±9.2
GapIndex points below the top.
Top
−0.5 · no clear gap
CoverageIndex weight that has results.
85% best
65%
SpeedOutput tokens per second.
88/s best
72/s
EloLMArena rating and rank.
1475
—
ReleasedMonth of release.
2026-08
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.07
$0.044 best
Output / 1MUS dollars per 1M output tokens.
$1.40
$0.176 best
1K chats2K tokens in, 500 out, each.
$0.84
$0.175 best
1K documents20K tokens in, 1K out, each.
$2.80
$1.05 best
1K agent tasks200K tokens in, 20K out, each.
$41.98
$12.26 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
67.9
71.1 best
CodingCode writing and repair.
65.9 best
50.8
ReasoningLogic problems and puzzles.
64.2
—
MultimodalTasks with images and text.
—
53.6
KnowledgeFacts and expert knowledge.
59.0
79.1 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
66.5
—
MathMath problems.
62.8
—
Benchmarks
4 sharedOnly GLM-5.3: 94Only Hy4 flash: 5
GLM-5.3
Hy4 flash