Qwen3.5-27B vs Qwen3.5-35B-A3B
Change modelsQwen3.5-27BAlibaba
Qwen3.5-35B-A3BAlibaba
IndexAll categories, out of 100.
51.3 ±4.3 best
49.4 ±3.2
GapIndex points below the top.
Top
−1.9 · no clear gap
CoverageIndex weight that has results.
90%
100% best
SpeedOutput tokens per second.
69/s best
43/s
EloLMArena rating and rank.
1409 best
1395
ReleasedMonth of release.
2026-03
2026-03
Input / 1MUS dollars per 1M input tokens.
$0.26
$0.14 best
Output / 1MUS dollars per 1M output tokens.
$2.60
$1.00 best
1K chats2K tokens in, 500 out, each.
$1.82
$0.78 best
1K documents20K tokens in, 1K out, each.
$7.80
$3.80 best
1K agent tasks200K tokens in, 20K out, each.
$104.00
$48.00 best
ContextMaximum tokens in one request.
262K
262K
AgenticMulti-step tasks with tools.
50.3 best
47.3
CodingCode writing and repair.
52.7 best
49.0
ReasoningLogic problems and puzzles.
50.5 best
48.5
MultimodalTasks with images and text.
53.9
55.1 best
KnowledgeFacts and expert knowledge.
49.0 best
47.4
MultilingualTasks in many languages.
51.6 best
50.4
InstructionTasks with strict prompt rules.
57.1 best
52.5
MathMath problems.
—
49.6
Benchmarks
28 sharedOnly Qwen3.5-27B: 1Only Qwen3.5-35B-A3B: 3
Qwen3.5-27B
Qwen3.5-35B-A3B