Qwen3.6-35B-A3B vs Qwen3.6 Plus

Change models
IndexAll categories, out of 100.
50.6 ±3.1
54.6 ±2.1 best
GapIndex points below the top.
−4.0
Top
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
65/s best
44/s
EloLMArena rating and rank.
—
1436
ReleasedMonth of release.
2026-04
2026-04
Input / 1MUS dollars per 1M input tokens.
$0.10 best
$0.325
Output / 1MUS dollars per 1M output tokens.
$0.90 best
$1.95
1K chats2K tokens in, 500 out, each.
$0.65 best
$1.63
1K documents20K tokens in, 1K out, each.
$2.90 best
$8.45
1K agent tasks200K tokens in, 20K out, each.
$38.00 best
$104.00
ContextMaximum tokens in one request.
262K
1M best
AgenticMulti-step tasks with tools.
52.7
55.0 best
CodingCode writing and repair.
49.6
56.2 best
ReasoningLogic problems and puzzles.
49.9
51.2 best
MultimodalTasks with images and text.
51.5
56.1 best
KnowledgeFacts and expert knowledge.
49.8
54.1 best
MultilingualTasks in many languages.
—
54.1
InstructionTasks with strict prompt rules.
49.2
52.4 best
MathMath problems.
49.0
54.9 best

Benchmarks

40 shared
Only Qwen3.6-35B-A3B: 13Only Qwen3.6 Plus: 51
Qwen3.6-35B-A3B
Qwen3.6 Plus
22.2%106 / 222
27.8% best92 / 222
71.7%106 / 217
78.3% best63 / 217
84.8%72 / 217
88.4% best54 / 217
0.3%137 / 214
2.9% best98 / 214
68.9%102 / 200
93.3% best51 / 200
84.1%85 / 199
88.2% best52 / 199
95.3%21 / 149
97.7% best9 / 149
64.4%57 / 146
75.2% best25 / 146
86.0%48 / 141
90.4% best27 / 141
19.6%82 / 133
24.5% best74 / 133
73.4%53 / 114
78.8% best26 / 114
75.0%53 / 113
78.0% best39 / 113
20.4%77 / 90
32.3% best68 / 90
49.5%72 / 83
56.6% best47 / 83
22.0% best41 / 80
12.0%61 / 80
21.4%62 / 77
28.8% best51 / 77
85.2%18 / 75
88.5% best3 / 75
80.4%29 / 59
87.1% best17 / 59
75.3%35 / 53
78.8% best21 / 53
42.6%32 / 52
50.6% best21 / 52