GLM-4.6 vs GPT-5 nano

Change models
IndexAll categories, out of 100.
41.8 ±5.4
41.9 ±6.2 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
85% best
75%
SpeedOutput tokens per second.
30/s
81/s best
EloLMArena rating and rank.
1440 best
1320
ReleasedMonth of release.
2025-09
2025-08
Input / 1MUS dollars per 1M input tokens.
$0.50
$0.05 best
Output / 1MUS dollars per 1M output tokens.
$2.00
$0.40 best
Batch output / 1MBatch price per 1M output tokens.
—
$0.20
1K chats2K tokens in, 500 out, each.
$2.00
$0.30 best
1K documents20K tokens in, 1K out, each.
$12.00
$1.40 best
1K agent tasks200K tokens in, 20K out, each.
$140.00
$18.00 best
ContextMaximum tokens in one request.
205K
400K best
AgenticMulti-step tasks with tools.
48.8
—
CodingCode writing and repair.
46.7 best
37.2
ReasoningLogic problems and puzzles.
31.1
42.6 best
MultimodalTasks with images and text.
—
47.5
KnowledgeFacts and expert knowledge.
39.0 best
37.4
MultilingualTasks in many languages.
—
44.5
InstructionTasks with strict prompt rules.
23.3
—
MathMath problems.
44.9
45.8 best

Benchmarks

14 shared
Only GLM-4.6: 13Only GPT-5 nano: 26
GLM-4.6
GPT-5 nano
79.6% best95 / 149
50.1%147 / 149
TaxEval v2Finance
66.2%113 / 143
67.4% best107 / 143
81.0% best64 / 142
70.2%88 / 142
74.5% best83 / 135
63.4%105 / 135
MMLU ProKnowledge
82.2% best78 / 135
76.1%107 / 135
AIMEMath
92.7% best17 / 95
81.2%45 / 95
MedQAHealthcare
92.2%34 / 95
93.3% best23 / 95
MGSMMultilingual
89.7% best44 / 74
89.3%47 / 74
3.8%50 / 69
8.3% best40 / 69
61.8% best28 / 65
34.8%53 / 65
0.0%33 / 64
20.0% best26 / 64
2.1% best35 / 55
0.0%45 / 55
55.4% best16 / 46
34.8%30 / 46
0.0%3 / 36
0.0%3 / 36