Compare · ModelsLive · 2 picked · head to head

Gemma 4 31B vs Qwen3.5 397B A17B

Side by side · benchmarks, pricing, and signals you can act on.

CiteAdd another

Winner summary

Qwen3.5 397B A17B wins on 9/18 benchmarks

Qwen3.5 397B A17B wins 9 of 18 shared benchmarks. Leads in arena · knowledge · general.

Category leads

speed·Gemma 4 31Barena·Qwen3.5 397B A17Bknowledge·Qwen3.5 397B A17Bgeneral·Qwen3.5 397B A17Bmath·Qwen3.5 397B A17B

Hype vs Reality

Attention vs performance

Gemma 4 31B

#101 by perf·#8 by attention

DESERVED

Qwen3.5 397B A17B

#48 by perf·#2 by attention

DESERVED

See full mindshare →

Best value

Gemma 4 31B

8.3x better value than Qwen3.5 397B A17B

Gemma 4 31B

245.6 pts/$

$0.22/M

Qwen3.5 397B A17B

29.6 pts/$

$2.02/M

Explore pricing →

Vendor risk

Who is behind the model

Google DeepMind

$4.20T·Tier 1

Low risk

Alibaba (Qwen)

$293.0B·Tier 1

Low risk

See the AI economy →

Head to head

18 benchmarks · 2 models

Gemma 4 31BQwen3.5 397B A17B

Artificial Analysis · CritPt

Gemma 4 31B leads by +0.5

Gemma 4 31B

1.4

Qwen3.5 397B A17B

0.9

Artificial Analysis · GDPval

Qwen3.5 397B A17B leads by +8.3

Gemma 4 31B

5.7

Qwen3.5 397B A17B

14.0

Artificial Analysis · GPQA Diamond

Qwen3.5 397B A17B leads by +0.4

Gemma 4 31B

85.7

Qwen3.5 397B A17B

86.1

Artificial Analysis · Humanity's Last Exam

Gemma 4 31B leads by +3.8

Gemma 4 31B

23.6

Qwen3.5 397B A17B

19.8

Artificial Analysis · IFBench

Gemma 4 31B leads by +24.0

Gemma 4 31B

75.6

Qwen3.5 397B A17B

51.6

Artificial Analysis · Long Context Reasoning

Gemma 4 31B leads by +5.4

Gemma 4 31B

69.7

Qwen3.5 397B A17B

64.3

Artificial Analysis · MMMU Pro

Gemma 4 31B leads by +20.7

Gemma 4 31B

73.4

Qwen3.5 397B A17B

52.7

Artificial Analysis · Quality Index

Qwen3.5 397B A17B leads by +6.8

Gemma 4 31B

14.7

Qwen3.5 397B A17B

21.4

Artificial Analysis · SciCode

Gemma 4 31B leads by +0.7

Gemma 4 31B

45.5

Qwen3.5 397B A17B

44.8

Artificial Analysis · tau2-Bench Telecom

Qwen3.5 397B A17B leads by +24.0

Gemma 4 31B

59.9

Qwen3.5 397B A17B

83.9

Artificial Analysis · Terminal-Bench Hard

Gemma 4 31B leads by +0.8

Gemma 4 31B

36.4

Qwen3.5 397B A17B

35.6

Chatbot Arena Elo · Coding

Qwen3.5 397B A17B leads by +34.8

Gemma 4 31B

1364.7

Qwen3.5 397B A17B

1399.4

Chatbot Arena Elo · Overall

Gemma 4 31B leads by +11.0

Gemma 4 31B

1452.8

Qwen3.5 397B A17B

1441.8

Chess Puzzles

Qwen3.5 397B A17B leads by +8.4

Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.

Gemma 4 31B

0.0

Qwen3.5 397B A17B

8.5

Dtbench

Qwen3.5 397B A17B leads by +8.0

Gemma 4 31B

71.1

Qwen3.5 397B A17B

79.1

GPQA diamond

Qwen3.5 397B A17B leads by +14.1

Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.

Gemma 4 31B

67.7

Qwen3.5 397B A17B

81.8

Lmca

Gemma 4 31B leads by +1.6

Gemma 4 31B

46.2

Qwen3.5 397B A17B

44.6

OTIS Mock AIME 2024-2025

Qwen3.5 397B A17B leads by +15.6

OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.

Gemma 4 31B

73.3

Qwen3.5 397B A17B

88.9

Full benchmark table

Benchmark	Gemma 4 31B	Qwen3.5 397B A17B
Artificial Analysis · CritPt	1.4	0.9
Artificial Analysis · GDPval	5.7	14.0
Artificial Analysis · GPQA Diamond	85.7	86.1
Artificial Analysis · Humanity's Last Exam	23.6	19.8
Artificial Analysis · IFBench	75.6	51.6
Artificial Analysis · Long Context Reasoning	69.7	64.3
Artificial Analysis · MMMU Pro	73.4	52.7
Artificial Analysis · Quality Index	14.7	21.4
Artificial Analysis · SciCode	45.5	44.8
Artificial Analysis · tau2-Bench Telecom	59.9	83.9
Artificial Analysis · Terminal-Bench Hard	36.4	35.6
Chatbot Arena Elo · Coding	1364.7	1399.4
Chatbot Arena Elo · Overall	1452.8	1441.8
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.	0.0	8.5
Dtbench	71.1	79.1
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.	67.7	81.8
Lmca	46.2	44.6
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.	73.3	88.9

Pricing · per 1M tokens · projected $/mo at 10M tokens

Model	Input	Output	Context	Projected $/mo
Gemma 4 31B	$0.09	$0.34	262K tokens (~131 books)	$1.53
Qwen3.5 397B A17B	$0.55	$3.50	262K tokens (~131 books)	$12.88

People also compared

Qwen3 30B A3B Thinking 2507 vs Qwen3.5 397B A17B Qwen3.5 397B A17B vs Qwen3 Next 80B A3B Thinking Qwen3.5 397B A17B vs Qwen3.7 Max Qwen-14B vs Qwen3.5 397B A17B