Inference
EN

GLM-5.2 vs Qwen3.7 Max

Change models
GLM-5.2Z.AI
Qwen3.7 MaxAlibaba
IndexAll categories, out of 100.
60.6 ±3.8 best
60.5 ±3.2
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
85%
90% best
SpeedOutput tokens per second.
111/s best
68/s
EloLMArena rating and rank.
1469
1475 best
ReleasedMonth of release.
2026-06
2026-05
Input / 1MUS dollars per 1M input tokens.
<$0.01 best
$1.48
Output / 1MUS dollars per 1M output tokens.
$6.80
$4.43 best
Batch output / 1MBatch price per 1M output tokens.
$0.989
—
1K chats2K tokens in, 500 out, each.
$3.41 best
$5.16
1K documents20K tokens in, 1K out, each.
$6.94 best
$33.93
1K agent tasks200K tokens in, 20K out, each.
$137.40 best
$383.50
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
61.7 best
60.5
CodingCode writing and repair.
63.5 best
59.8
ReasoningLogic problems and puzzles.
58.6
60.4 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
55.7
58.6 best
MultilingualTasks in many languages.
—
57.2
InstructionTasks with strict prompt rules.
55.1
64.4 best
MathMath problems.
59.6
62.1 best

Benchmarks

56 shared
Only GLM-5.2: 21Only Qwen3.7 Max: 26
GLM-5.2
Qwen3.7 Max
Artificial Analysis Humanity's Last ExamKnowledge
41.1% best42 / 222
40.5%46 / 222
Artificial Analysis Long Context ReasoningReasoning
78.3%63 / 217
79.0% best58 / 217
GPQA diamond · Epoch AIKnowledge
91.9% best29 / 217
90.9%35 / 217
Critical Physics TasksReasoning
20.9% best26 / 214
13.4%54 / 214
OTIS Mock AIME 2024-2025Math
86.4%73 / 200
95.6% best40 / 200
Artificial Analysis GPQA DiamondKnowledge
89.5%43 / 199
92.3% best19 / 199
Artificial Analysis Omniscience AccuracyKnowledge
24.3%108 / 164
31.1% best76 / 164
LegalBenchLegal
84.1%39 / 149
84.9% best28 / 149
τ²-Bench Tool-Agent-User EvaluationAgentic
99.1% best1 / 149
94.7%24 / 149
Artificial Analysis IFBenchInstruction
73.3%29 / 146
80.5% best4 / 146
TaxEval v2Finance
73.3%50 / 143
75.3% best19 / 143
LiveCodeBenchCoding
69.5%92 / 142
87.1% best19 / 142
Graduate-Level Google-Proof Q&AKnowledge
91.2%23 / 141
92.4% best16 / 141
GPQA Diamond · Vals AIKnowledge
85.6%45 / 135
90.2% best25 / 135
MMLU ProKnowledge
86.7%39 / 135
89.3% best12 / 135
GDPval-AA normalizedAgentic
43.6% best42 / 133
31.4%59 / 133
CorpFin v2Finance
66.1% best21 / 131
63.7%40 / 131
Vibe Code Bench v1.1Coding
64.0% best56 / 123
47.7%71 / 123
Artificial Analysis SciCodeCoding
51.2% best47 / 114
49.5%54 / 114
MedScribeHealthcare
83.5% best46 / 109
79.4%63 / 109