Compare · ModelsLive · 2 picked · head to head
Gemma 4 31B vs Qwen3.5-35B-A3B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemma 4 31B wins on 5/8 benchmarks
Gemma 4 31B wins 5 of 8 shared benchmarks. Leads in arena · general · math.
Category leads
speed·Qwen3.5-35B-A3Barena·Gemma 4 31Bknowledge·Qwen3.5-35B-A3Bgeneral·Gemma 4 31Bmath·Gemma 4 31B
Hype vs Reality
Attention vs performance
Gemma 4 31B
#101 by perf·#7 by attention
Qwen3.5-35B-A3B
#114 by perf·#2 by attention
Best value
Gemma 4 31B
2.8x better value than Qwen3.5-35B-A3B
Gemma 4 31B
245.6 pts/$
$0.22/M
Qwen3.5-35B-A3B
88.5 pts/$
$0.57/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
Alibaba (Qwen)
$293.0B·Tier 1
Head to head
8 benchmarks · 2 models
Gemma 4 31BQwen3.5-35B-A3B
Artificial Analysis · Quality Index
Qwen3.5-35B-A3B leads by +8.7
Gemma 4 31B
14.7
Qwen3.5-35B-A3B
23.4
Chatbot Arena Elo · Coding
Gemma 4 31B leads by +111.3
Gemma 4 31B
1364.7
Qwen3.5-35B-A3B
1253.4
Chatbot Arena Elo · Overall
Gemma 4 31B leads by +59.0
Gemma 4 31B
1452.8
Qwen3.5-35B-A3B
1393.8
Chess Puzzles
Qwen3.5-35B-A3B leads by +5.3
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
Qwen3.5-35B-A3B
5.3
Dtbench
Gemma 4 31B leads by +4.5
Gemma 4 31B
71.1
Qwen3.5-35B-A3B
66.7
GPQA diamond
Qwen3.5-35B-A3B leads by +10.3
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
Qwen3.5-35B-A3B
78.0
Lmca
Gemma 4 31B leads by +11.5
Gemma 4 31B
46.2
Qwen3.5-35B-A3B
34.7
OTIS Mock AIME 2024-2025
Gemma 4 31B leads by +3.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemma 4 31B
73.3
Qwen3.5-35B-A3B
70.0
Full benchmark table
| Benchmark | Gemma 4 31B | Qwen3.5-35B-A3B |
|---|---|---|
Artificial Analysis · Quality Index | 14.7 | 23.4 |
Chatbot Arena Elo · Coding | 1364.7 | 1253.4 |
Chatbot Arena Elo · Overall | 1452.8 | 1393.8 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 0.0 | 5.3 |
Dtbench | 71.1 | 66.7 |
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 | 78.0 |
Lmca | 46.2 | 34.7 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 73.3 | 70.0 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.09 | $0.34 | 262K tokens (~131 books) | $1.53 | |
| $0.15 | $1.00 | 262K tokens (~131 books) | $3.63 |