Qwen3.5-122B-A10B vs Qwen3.5-27B
Change modelsQwen3.5-122B-A10BAlibaba
Qwen3.5-27BAlibaba
IndexAll categories, out of 100.
51.9 ±4.3 best
51.3 ±4.3
GapIndex points below the top.
Top
−0.6 · no clear gap
CoverageIndex weight that has results.
90%
90%
SpeedOutput tokens per second.
70/s best
69/s
EloLMArena rating and rank.
1417 best
1409
ReleasedMonth of release.
2026-03
2026-03
Input / 1MUS dollars per 1M input tokens.
$0.26
$0.26
Output / 1MUS dollars per 1M output tokens.
$2.08 best
$2.60
1K chats2K tokens in, 500 out, each.
$1.56 best
$1.82
1K documents20K tokens in, 1K out, each.
$7.28 best
$7.80
1K agent tasks200K tokens in, 20K out, each.
$93.60 best
$104.00
ContextMaximum tokens in one request.
262K
262K
AgenticMulti-step tasks with tools.
51.4 best
50.3
CodingCode writing and repair.
50.4
52.7 best
ReasoningLogic problems and puzzles.
50.3
50.5 best
MultimodalTasks with images and text.
53.9
53.9
KnowledgeFacts and expert knowledge.
52.9 best
49.0
MultilingualTasks in many languages.
51.6
51.6
InstructionTasks with strict prompt rules.
55.5
57.1 best
MathMath problems.
—
—
Benchmarks
25 sharedOnly Qwen3.5-122B-A10B: 3Only Qwen3.5-27B: 4
Qwen3.5-122B-A10B
Qwen3.5-27B