GLM-5.1 vs GPT-5.1

Change models
GPT-5.1OpenAI
IndexAll categories, out of 100.
55.0 ±4.1
55.0 ±3.7
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
85%
95% best
SpeedOutput tokens per second.
33/s
66/s best
EloLMArena rating and rank.
1463 best
1422
ReleasedMonth of release.
2026-04
2025-11
Input / 1MUS dollars per 1M input tokens.
$1.19 best
$1.25
Output / 1MUS dollars per 1M output tokens.
$3.74 best
$10.00
Batch output / 1MBatch price per 1M output tokens.
—
$5.00
1K chats2K tokens in, 500 out, each.
$4.25 best
$7.50
1K documents20K tokens in, 1K out, each.
$27.54 best
$35.00
1K agent tasks200K tokens in, 20K out, each.
$312.80 best
$450.00
ContextMaximum tokens in one request.
205K
400K best
AgenticMulti-step tasks with tools.
57.7 best
53.4
CodingCode writing and repair.
56.2 best
52.9
ReasoningLogic problems and puzzles.
50.4
55.4 best
MultimodalTasks with images and text.
—
57.7
KnowledgeFacts and expert knowledge.
51.5
56.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
59.3 best
56.3
MathMath problems.
54.1
56.8 best

Benchmarks

30 shared
Only GLM-5.1: 30Only GPT-5.1: 14
GLM-5.1
GPT-5.1
89.9% best44 / 220
87.6%65 / 220
30.1% best77 / 216
28.5%84 / 216
73.7%95 / 211
80.0% best43 / 211
4.6%85 / 207
4.9% best82 / 207
93.3% best54 / 203
88.6%70 / 203
86.8%58 / 193
87.3% best55 / 193
23.7%112 / 170
37.7% best65 / 170
84.4%33 / 149
85.7% best20 / 149
TaxEval v2Finance
71.2%80 / 143
74.9% best26 / 143
97.7% best9 / 143
81.9%63 / 143
81.4%62 / 142
86.5% best22 / 142
76.3% best12 / 140
72.9%32 / 140
84.5%50 / 135
86.6% best41 / 135
MMLU ProKnowledge
86.9% best37 / 135
86.4%42 / 135
30.8% best62 / 132
16.3%84 / 132
CorpFin v2Finance
64.5% best35 / 131
63.8%39 / 131
31.5% best88 / 130
24.6%92 / 130
36.4%72 / 120
39.9% best68 / 120
MedScribeHealthcare
72.3%91 / 111
88.1% best15 / 111
MedCodeHealthcare
41.6%53 / 108
52.7% best13 / 108