Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

MiMo-V2.5-Pro vs Qwen3 VL 32B Thinking

X

Xiaomi 🇨🇳

58.0

#147—

Q

Qwen3 VL 32B Thinking

Alibaba Cloud / Qwen Team 🇨🇳

57.9

#150—

Category Comparison

Benchmark-by-Benchmark

reasoning

Benchmark	MiMo-V2.5-Pro	Qwen3 VL 32B Thinking
GPQA Diamond	66.7	73.1
Humanity's Last Exam	34	—

coding

Benchmark	MiMo-V2.5-Pro	Qwen3 VL 32B Thinking
SWE-bench Verified	78.9	—
SWE-Bench Pro	57.2	—

math

Benchmark	MiMo-V2.5-Pro	Qwen3 VL 32B Thinking
AIME 2025	—	83.7

multimodal

Benchmark	MiMo-V2.5-Pro	Qwen3 VL 32B Thinking
MMMU-Pro	—	68.1
CharXiv Reasoning	—	65.2
ScreenSpot Pro	—	57.1

general

Benchmark	MiMo-V2.5-Pro	Qwen3 VL 32B Thinking
SimpleQA	—	55.4

agent

Benchmark	MiMo-V2.5-Pro	Qwen3 VL 32B Thinking
OSWorld	—	41

Category Winners

coding

X

MiMo-V2.5-Pro

64.9

math

Q

Qwen3 VL 32B Thinking

58.5

reasoning

Q

Qwen3 VL 32B Thinking

60.4

general

Q

Qwen3 VL 32B Thinking

75.1

multimodal

Q

Qwen3 VL 32B Thinking

35.2

agent

Q

Qwen3 VL 32B Thinking

39.4

MiMo-V2.5-Pro vs Qwen3 VL 32B Thinking — Benchmark Comparison | Neura Market