Inference
EN

Qwen3.5 Plus Thinking vs Kimi K2 Thinking

Change models
Qwen3.5 Plus ThinkingAlibaba
Kimi K2 ThinkingMoonshot AI
IndexAll categories, out of 100.
48.1 ±8.2
48.2 ±8.6 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
75% best
65%
SpeedOutput tokens per second.
—
48/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
—
2025-11
Input / 1MUS dollars per 1M input tokens.
—
$0.60
Output / 1MUS dollars per 1M output tokens.
—
$2.50
1K chats2K tokens in, 500 out, each.
—
$2.45
1K documents20K tokens in, 1K out, each.
—
$14.50
1K agent tasks200K tokens in, 20K out, each.
—
$170.00
ContextMaximum tokens in one request.
—
262K
AgenticMulti-step tasks with tools.
51.6 best
48.0
CodingCode writing and repair.
53.9 best
44.9
ReasoningLogic problems and puzzles.
—
—
MultimodalTasks with images and text.
5.0
—
KnowledgeFacts and expert knowledge.
55.8 best
49.2
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
53.1 best
50.5

Benchmarks

11 shared
Only Qwen3.5 Plus Thinking: 3Only Kimi K2 Thinking: 11
Qwen3.5 Plus Thinking
Kimi K2 Thinking
LegalBenchLegal
85.1% best25 / 149
80.2%89 / 149
LiveCodeBenchCoding
85.3% best33 / 142
63.1%102 / 142
GPQA Diamond · Vals AIKnowledge
87.4% best38 / 135
78.5%72 / 135
MMLU ProKnowledge
87.2% best32 / 135
81.1%84 / 135
CorpFin v2Finance
65.3% best28 / 131
60.6%66 / 131
AIMEMath
86.0% best33 / 95
85.4%36 / 95
MedQAHealthcare
95.2% best13 / 95
92.6%29 / 95
SWE-benchCoding
71.2% best59 / 87
60.2%77 / 87
Terminal-Bench 2.0 · Vals AIAgentic
41.6% best29 / 66
37.1%38 / 66
CaseLaw v2Legal
59.7%25 / 53
65.7% best10 / 53
Finance Agent v1.1Finance
54.5% best16 / 51
36.6%42 / 51