Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

Kimi K2 0905 vs Qwen3.5-35B-A3B

M

Moonshot AI 🇨🇳

65.5

#113—

Q

Qwen3.5-35B-A3B

Alibaba Cloud / Qwen Team 🇨🇳

64.6

#116—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	Kimi K2 0905	Qwen3.5-35B-A3B
GPQA Diamond	75.8	84.2
Humanity's Last Exam	—	47.4

coding

Benchmark	Kimi K2 0905	Qwen3.5-35B-A3B
SWE-bench Verified	—	69.2

multimodal

Benchmark	Kimi K2 0905	Qwen3.5-35B-A3B
MMMU	—	81.4
MMMU-Pro	—	75.1
CharXiv Reasoning	—	77.5
ScreenSpot Pro	—	68.6

general

Benchmark	Kimi K2 0905	Qwen3.5-35B-A3B
MMMLU	—	85.2

agent

Benchmark	Kimi K2 0905	Qwen3.5-35B-A3B
BrowseComp	—	61

Category Winners

coding

Q

Qwen3.5-35B-A3B

58.6

reasoning

Q

Qwen3.5-35B-A3B

79.8

general

Q

Qwen3.5-35B-A3B

58.0

multimodal

Q

Qwen3.5-35B-A3B

67.3

agent

Q

Qwen3.5-35B-A3B

41.7

Kimi K2 0905 vs Qwen3.5-35B-A3B — Benchmark Comparison | Neura Market