dots3-note Preview vs Qwen3.7 Max

Change models
dots3-note PreviewDots Studio
IndexAll categories, out of 100.
63.4 ±3.9 best
60.5 ±3.2
GapIndex points below the top.
Top
−2.9 · no clear gap
CoverageIndex weight that has results.
95% best
90%
SpeedOutput tokens per second.
—
68/s
EloLMArena rating and rank.
—
1475
ReleasedMonth of release.
2026-08
2026-05
Input / 1MUS dollars per 1M input tokens.
Free best
$1.48
Output / 1MUS dollars per 1M output tokens.
Free best
$4.43
1K chats2K tokens in, 500 out, each.
Free best
$5.16
1K documents20K tokens in, 1K out, each.
Free best
$33.93
1K agent tasks200K tokens in, 20K out, each.
Free best
$383.50
ContextMaximum tokens in one request.
512K
1M best
AgenticMulti-step tasks with tools.
63.3 best
60.5
CodingCode writing and repair.
60.3 best
59.8
ReasoningLogic problems and puzzles.
74.5 best
60.4
MultimodalTasks with images and text.
59.2
—
KnowledgeFacts and expert knowledge.
77.2 best
58.6
MultilingualTasks in many languages.
—
57.2
InstructionTasks with strict prompt rules.
58.2
64.4 best
MathMath problems.
62.3 best
62.1

Benchmarks

10 shared
Only dots3-note Preview: 17Only Qwen3.7 Max: 72
dots3-note Preview
Qwen3.7 Max
78.4%27 / 114
80.4% best18 / 114
61.0% best31 / 83
60.6%32 / 83
52.6% best18 / 77
41.4%33 / 77
93.9%10 / 70
94.3% best8 / 70
91.5%7 / 59
91.6% best6 / 59
80.4% best11 / 57
79.1%19 / 57
Claw-EvalAgentic
73.4% best6 / 42
65.2%17 / 42
52.6%23 / 36
53.5% best22 / 36
NL2RepoCoding
49.8% best12 / 36
47.2%17 / 36
90.9% best1 / 10
90.0%2 / 10