dots3-note Preview vs Qwen3.6-35B-A3B

Change models
dots3-note PreviewDots Studio
IndexAll categories, out of 100.
63.4 ±3.9 best
50.6 ±3.1
GapIndex points below the top.
Top
−12.8
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
—
65/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-08
2026-04
Input / 1MUS dollars per 1M input tokens.
Free best
$0.10
Output / 1MUS dollars per 1M output tokens.
Free best
$0.90
1K chats2K tokens in, 500 out, each.
Free best
$0.65
1K documents20K tokens in, 1K out, each.
Free best
$2.90
1K agent tasks200K tokens in, 20K out, each.
Free best
$38.00
ContextMaximum tokens in one request.
512K best
262K
AgenticMulti-step tasks with tools.
63.3 best
52.7
CodingCode writing and repair.
60.3 best
49.6
ReasoningLogic problems and puzzles.
74.5 best
49.9
MultimodalTasks with images and text.
59.2 best
51.5
KnowledgeFacts and expert knowledge.
77.2 best
49.8
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
58.2 best
49.2
MathMath problems.
62.3 best
49.0

Benchmarks

10 shared
Only dots3-note Preview: 17Only Qwen3.6-35B-A3B: 43
dots3-note Preview
Qwen3.6-35B-A3B
78.4% best27 / 114
73.4%53 / 114
61.0% best31 / 83
49.5%72 / 83
52.6% best18 / 77
21.4%62 / 77
91.5% best7 / 59
80.4%29 / 59
79.1% best18 / 53
75.3%35 / 53
Claw-EvalAgentic
73.4% best6 / 42
68.7%12 / 42
NL2RepoCoding
49.8% best12 / 36
29.4%35 / 36
SimpleVQAMultimodal
72.5% best6 / 18
58.9%13 / 18
78.9% best7 / 16
60.1%15 / 16
VideoMMMUMultimodal
86.8%
83.7%