Qwen3.5-122B-A10B vs Qwen3.5 397B
Change modelsQwen3.5-122B-A10BAlibaba
Qwen3.5 397BAlibaba
IndexAll categories, out of 100.
51.9 ±4.3
53.8 ±2.4 best
GapIndex points below the top.
−1.9 · no clear gap
Top
CoverageIndex weight that has results.
90%
100% best
SpeedOutput tokens per second.
70/s best
59/s
EloLMArena rating and rank.
1417
—
ReleasedMonth of release.
2026-03
2026-02
Input / 1MUS dollars per 1M input tokens.
$0.26 best
$0.60
Output / 1MUS dollars per 1M output tokens.
$2.08 best
$3.60
1K chats2K tokens in, 500 out, each.
$1.56 best
$3.00
1K documents20K tokens in, 1K out, each.
$7.28 best
$15.60
1K agent tasks200K tokens in, 20K out, each.
$93.60 best
$192.00
ContextMaximum tokens in one request.
262K best
128K
AgenticMulti-step tasks with tools.
51.4
53.3 best
CodingCode writing and repair.
50.4
53.3 best
ReasoningLogic problems and puzzles.
50.3
51.9 best
MultimodalTasks with images and text.
53.9
55.6 best
KnowledgeFacts and expert knowledge.
52.9
53.8 best
MultilingualTasks in many languages.
51.6
55.6 best
InstructionTasks with strict prompt rules.
55.5
55.6 best
MathMath problems.
—
53.6
Benchmarks
24 sharedOnly Qwen3.5-122B-A10B: 4Only Qwen3.5 397B: 45
Qwen3.5-122B-A10B
Qwen3.5 397B