Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

MiMo-V2.5 vs Qwen3 VL 8B Thinking

X

Xiaomi 🇨🇳

50.1

#149—

Q

Qwen3 VL 8B Thinking

Alibaba Cloud / Qwen Team 🇨🇳

49.8

#152—

Category Comparison

Benchmark-by-Benchmark

coding

Benchmark	MiMo-V2.5	Qwen3 VL 8B Thinking
SWE-Bench Pro	56.1	—

multimodal

Benchmark	MiMo-V2.5	Qwen3 VL 8B Thinking
MMMU-Pro	77.9	60.4
CharXiv Reasoning	81	53
ScreenSpot Pro	—	46.6

reasoning

Benchmark	MiMo-V2.5	Qwen3 VL 8B Thinking
GPQA Diamond	—	69.9

math

Benchmark	MiMo-V2.5	Qwen3 VL 8B Thinking
AIME 2025	—	80.3

general

Benchmark	MiMo-V2.5	Qwen3 VL 8B Thinking
SimpleQA	—	49.6

agent

Benchmark	MiMo-V2.5	Qwen3 VL 8B Thinking
OSWorld	—	33.9

Category Winners

coding

X

MiMo-V2.5

38.1

math

Q

Qwen3 VL 8B Thinking

52.3

reasoning

Q

Qwen3 VL 8B Thinking

56.4

general

Q

Qwen3 VL 8B Thinking

67.0

multimodal

X

MiMo-V2.5

74.2

agent

Q

Qwen3 VL 8B Thinking

28.8

MiMo-V2.5 vs Qwen3 VL 8B Thinking — Benchmark Comparison | Neura Market