GLM-5.3 vs Ling 3.1 Flash

Change models
Ling 3.1 FlashInclusionAI
IndexAll categories, out of 100.
65.6 ±3.5
65.8 ±7.3 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
85% best
70%
SpeedOutput tokens per second.
88/s best
84/s
EloLMArena rating and rank.
1475
—
ReleasedMonth of release.
2026-08
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.07
$0.045 best
Output / 1MUS dollars per 1M output tokens.
$1.40
$0.135 best
1K chats2K tokens in, 500 out, each.
$0.84
$0.158 best
1K documents20K tokens in, 1K out, each.
$2.80
$1.04 best
1K agent tasks200K tokens in, 20K out, each.
$41.98
$11.70 best
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
67.9 best
66.2
CodingCode writing and repair.
65.9
66.5 best
ReasoningLogic problems and puzzles.
64.2
67.6 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
59.0
62.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
66.5
—
MathMath problems.
62.8
—

Benchmarks

9 shared
Only GLM-5.3: 89Only Ling 3.1 Flash: 9
GLM-5.3
Ling 3.1 Flash
42.3% best39 / 222
39.4%50 / 222
79.7%45 / 217
83.0% best18 / 217
19.1% best32 / 214
18.0%35 / 214
57.5% best12 / 133
55.9%16 / 133
59.0% best12 / 114
54.1%36 / 114
88.2% best10 / 86
81.2%31 / 86
DeepSWEAgentic
66.9% best32 / 61
59.7%44 / 61
48.2%17 / 33
52.5% best8 / 33
CyberGymAgentic
84.5%9 / 29
87.9% best4 / 29