dots3-note Preview vs Qwen3.5 397B

Change models
dots3-note PreviewDots Studio
IndexAll categories, out of 100.
63.4 ±3.9 best
53.8 ±2.4
GapIndex points below the top.
Top
−9.6
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
—
59/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-08
2026-02
Input / 1MUS dollars per 1M input tokens.
Free best
$0.60
Output / 1MUS dollars per 1M output tokens.
Free best
$3.60
1K chats2K tokens in, 500 out, each.
Free best
$3.00
1K documents20K tokens in, 1K out, each.
Free best
$15.60
1K agent tasks200K tokens in, 20K out, each.
Free best
$192.00
ContextMaximum tokens in one request.
512K best
128K
AgenticMulti-step tasks with tools.
63.3 best
53.3
CodingCode writing and repair.
60.3 best
53.3
ReasoningLogic problems and puzzles.
74.5 best
51.9
MultimodalTasks with images and text.
59.2 best
55.6
KnowledgeFacts and expert knowledge.
77.2 best
53.8
MultilingualTasks in many languages.
—
55.6
InstructionTasks with strict prompt rules.
58.2 best
55.6
MathMath problems.
62.3 best
53.6

Benchmarks

14 shared
Only dots3-note Preview: 13Only Qwen3.5 397B: 55
dots3-note Preview
Qwen3.5 397B
78.4% best27 / 114
76.2%42 / 114
61.0% best31 / 83
50.9%69 / 83
52.6% best18 / 77
28.7%52 / 77
93.9% best10 / 70
92.6%16 / 70
BrowseCompAgentic
83.3% best24 / 63
69.0%43 / 63
91.5% best7 / 59
83.6%25 / 59
80.4% best11 / 57
76.5%25 / 57
79.1% best18 / 53
79.0%19 / 53
Claw-EvalAgentic
73.4% best6 / 42
56.8%34 / 42
NL2RepoCoding
49.8% best12 / 36
32.2%33 / 36
MathVisionMultimodal
87.7%12 / 24
88.6% best10 / 24
SimpleVQAMultimodal
72.5% best6 / 18
67.1%10 / 18
78.9% best7 / 16
74.0%10 / 16
VideoMMMUMultimodal
86.8%
84.7%