dots3-note Preview vs GPT-5.4

Change models
dots3-note PreviewDots Studio
GPT-5.4OpenAI
IndexAll categories, out of 100.
63.4 ±3.9
64.8 ±2.5 best
GapIndex points below the top.
−1.4 · no clear gap
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
—
38/s
EloLMArena rating and rank.
—
1452
ReleasedMonth of release.
2026-08
2026-03
Input / 1MUS dollars per 1M input tokens.
Free best
$2.50
Output / 1MUS dollars per 1M output tokens.
Free best
$15.00
Batch output / 1MBatch price per 1M output tokens.
—
$7.50
1K chats2K tokens in, 500 out, each.
Free best
$12.50
1K documents20K tokens in, 1K out, each.
Free best
$65.00
1K agent tasks200K tokens in, 20K out, each.
Free best
$800.00
ContextMaximum tokens in one request.
512K
1.05M best
AgenticMulti-step tasks with tools.
63.3 best
62.1
CodingCode writing and repair.
60.3
61.8 best
ReasoningLogic problems and puzzles.
74.5 best
69.0
MultimodalTasks with images and text.
59.2
62.1 best
KnowledgeFacts and expert knowledge.
77.2 best
66.4
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
58.2
63.4 best
MathMath problems.
62.3
68.0 best

Benchmarks

9 shared
Only dots3-note Preview: 18Only GPT-5.4: 90
dots3-note Preview
GPT-5.4
76.8% best22 / 131
74.0%24 / 131
61.0% best31 / 83
57.7%41 / 83
52.6% best18 / 77
52.1%20 / 77
BrowseCompAgentic
83.3% best24 / 63
82.7%27 / 63
79.1%18 / 53
81.2% best10 / 53
Claw-EvalAgentic
73.4% best6 / 42
60.3%27 / 42
92.1% best8 / 24
73.6%20 / 24
SimpleVQAMultimodal
72.5% best6 / 18
61.1%12 / 18
ZeroBenchMultimodal
19.0%8 / 10
41.0% best2 / 10