Neura Intelligence Index

AI Model Benchmarks

Back to Leaderboard

Mercury 2 vs Qwen3.6-35B-A3B

I

Inception 🇺🇸

49.8

#150—

Q

Qwen3.6-35B-A3B

Alibaba Cloud / Qwen Team 🇨🇳

49.6

#153—

Category Comparison

Benchmark-by-Benchmark

coding

Benchmark	Mercury 2	Qwen3.6-35B-A3B
SciCode	38	—
SWE-bench Verified	—	73.4
SWE-Bench Pro	—	49.5

reasoning

Benchmark	Mercury 2	Qwen3.6-35B-A3B
GPQA Diamond	74	86
Humanity's Last Exam	—	21.4

math

Benchmark	Mercury 2	Qwen3.6-35B-A3B
AIME 2025	91.1	—

multimodal

Benchmark	Mercury 2	Qwen3.6-35B-A3B
MMMU	—	81.7
MMMU-Pro	—	75.3
CharXiv Reasoning	—	78

agent

Benchmark	Mercury 2	Qwen3.6-35B-A3B
Toolathlon	—	26.9
MCP Atlas	—	62.8

Category Winners

coding

Q

Qwen3.6-35B-A3B

39.5

math

I

Mercury 2

71.6

reasoning

I

Mercury 2

64.3

multimodal

Q

Qwen3.6-35B-A3B

73.0

agent

Q

Qwen3.6-35B-A3B

14.4

Mercury 2 vs Qwen3.6-35B-A3B — Benchmark Comparison | Neura Market