GLM-5 vs o3

Change models
GLM-5Z.AI
o3OpenAI
IndexAll categories, out of 100.
51.6 ±3.6
51.8 ±3.9 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
90%
95% best
SpeedOutput tokens per second.
45/s
65/s best
EloLMArena rating and rank.
1446 best
1410
ReleasedMonth of release.
2026-02
2025-04
Input / 1MUS dollars per 1M input tokens.
$1.00 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$3.20 best
$8.00
Batch output / 1MBatch price per 1M output tokens.
—
$4.00
1K chats2K tokens in, 500 out, each.
$3.60 best
$8.00
1K documents20K tokens in, 1K out, each.
$23.20 best
$48.00
1K agent tasks200K tokens in, 20K out, each.
$264.00 best
$560.00
ContextMaximum tokens in one request.
205K best
200K
AgenticMulti-step tasks with tools.
51.6
51.8 best
CodingCode writing and repair.
53.5 best
51.0
ReasoningLogic problems and puzzles.
48.3
52.9 best
MultimodalTasks with images and text.
—
53.1
KnowledgeFacts and expert knowledge.
51.8
53.7 best
MultilingualTasks in many languages.
52.5
—
InstructionTasks with strict prompt rules.
53.1
55.7 best
MathMath problems.
52.5 best
49.1

Benchmarks

20 shared
Only GLM-5: 43Only o3: 26
GLM-5
o3
29.3% best84 / 222
20.1%112 / 222
75.7% best92 / 217
74.7%97 / 217
87.8% best60 / 217
81.8%82 / 217
2.0% best105 / 214
1.1%118 / 214
80.0%86 / 200
83.9% best78 / 200
82.0%92 / 199
82.7% best91 / 199
98.2% best7 / 149
80.7%67 / 149
72.3% best37 / 146
71.4%38 / 146
4.9%80 / 131
6.5% best72 / 131
44.7%79 / 126
60.8% best67 / 126
5.4% best65 / 122
2.9%80 / 122
58.6%70 / 116
64.3% best63 / 116
16.4%33 / 69
18.7% best32 / 69
72.8% best7 / 65
58.4%33 / 65
2.1%32 / 64
10.0% best29 / 64
2.1%35 / 55
2.1%35 / 55
0.0%3 / 36
0.0%3 / 36
72.1% best22 / 32
62.3%27 / 32
73.7%18 / 23
73.9% best17 / 23
82.5% best3 / 22
52.0%21 / 22