Compare · ModelsLive · 2 picked · head to head
Gemini 3.1 Pro Preview vs Gemma 4 31B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.1 Pro Preview wins on 20/20 benchmarks
Gemini 3.1 Pro Preview wins 20 of 20 shared benchmarks. Leads in speed · arena · knowledge.
Category leads
speed·Gemini 3.1 Pro Previewarena·Gemini 3.1 Pro Previewknowledge·Gemini 3.1 Pro Previewgeneral·Gemini 3.1 Pro Previewmath·Gemini 3.1 Pro Previewcoding·Gemini 3.1 Pro Preview
Head to head · from the data · data as of 2026-11-17
- Benchmarks · Gemini 3.1 Pro Preview leads on 20 of 20 shared benchmarks (Artificial Analysis · CritPt, Artificial Analysis · GDPval, Artificial Analysis · GPQA Diamond, Artificial Analysis · Humanity's Last Exam, 16 more), Gemma 4 31B on 0
- Price · Gemini 3.1 Pro Preview input $2.00/M vs Gemma 4 31B $0.20/M, Gemma 4 31B is 90% cheaper (OpenRouter list price, as of 2026-11-17)
- Cheapest provider · Gemini 3.1 Pro Preview at Google and 1 other provider $1.00/M input (of 6 offers) as of 2026-11-17 · Gemma 4 31B at PrimeIntellect $0.07/M input (of 18 offers) as of 2026-11-17
- Context · Gemini 3.1 Pro Preview 1.0M tokens vs Gemma 4 31B 262K tokens
- Released · Gemini 3.1 Pro Preview Feb 19, 2026 vs Gemma 4 31B Apr 2, 2026 · 2 months apart
- Open weights · Gemma 4 31B has open weights (on Hugging Face as google/gemma-4-31B-it)
- Price history · Gemini 3.1 Pro Preview OpenRouter input list price had no move of 5% or more in the 90 days to 2026-11-17
Sources · scores from public leaderboards, list prices and provider offers from OpenRouter, price moves from the BenchGecko changelog (5% or more, held in the next daily check), Gecko tests run by BenchGecko.
Hype vs Reality
Attention vs performance
Gemini 3.1 Pro Preview
#143 by perf·#9 by attention
Gemma 4 31B
#109 by perf·#4 by attention
Best value
Gemma 4 31B
25.2x better value than Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview
7.0 pts/$
$7.00/M
Gemma 4 31B
176.7 pts/$
$0.30/M
Vendor risk
Who is behind the model
Google DeepMind
$3.49T·Tier 1
Google DeepMind
$3.49T·Tier 1
Head to head
20 benchmarks · 2 models
Gemini 3.1 Pro PreviewGemma 4 31B
Artificial Analysis · CritPt
Gemini 3.1 Pro Preview leads by +16.3
Gemini 3.1 Pro Preview
17.7
Gemma 4 31B
1.4
Artificial Analysis · GDPval
Gemini 3.1 Pro Preview leads by +8.6
Gemini 3.1 Pro Preview
14.6
Gemma 4 31B
6.0
Artificial Analysis · GPQA Diamond
Gemini 3.1 Pro Preview leads by +8.4
Gemini 3.1 Pro Preview
94.1
Gemma 4 31B
85.7
Artificial Analysis · Humanity's Last Exam
Gemini 3.1 Pro Preview leads by +23.4
Gemini 3.1 Pro Preview
47.0
Gemma 4 31B
23.6
Artificial Analysis · IFBench
Gemini 3.1 Pro Preview leads by +1.5
Gemini 3.1 Pro Preview
77.1
Gemma 4 31B
75.6
Artificial Analysis · Long Context Reasoning
Gemini 3.1 Pro Preview leads by +12.3
Gemini 3.1 Pro Preview
82.0
Gemma 4 31B
69.7
Artificial Analysis · MMMU Pro
Gemini 3.1 Pro Preview leads by +9.0
Gemini 3.1 Pro Preview
82.4
Gemma 4 31B
73.4
Artificial Analysis · Quality Index
Gemini 3.1 Pro Preview leads by +15.0
Gemini 3.1 Pro Preview
29.7
Gemma 4 31B
14.7
Artificial Analysis · SciCode
Gemini 3.1 Pro Preview leads by +13.2
Gemini 3.1 Pro Preview
58.7
Gemma 4 31B
45.5
Artificial Analysis · tau2-Bench Telecom
Gemini 3.1 Pro Preview leads by +35.7
Gemini 3.1 Pro Preview
95.6
Gemma 4 31B
59.9
Artificial Analysis · Terminal-Bench Hard
Gemini 3.1 Pro Preview leads by +17.4
Gemini 3.1 Pro Preview
53.8
Gemma 4 31B
36.4
Chatbot Arena Elo · Coding
Gemini 3.1 Pro Preview leads by +81.5
Gemini 3.1 Pro Preview
1446.2
Gemma 4 31B
1364.7
Chatbot Arena Elo · Overall
Gemini 3.1 Pro Preview leads by +34.1
Gemini 3.1 Pro Preview
1487.0
Gemma 4 31B
1452.8
Chess Puzzles
Gemini 3.1 Pro Preview leads by +48.4
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
Gemini 3.1 Pro Preview
48.4
Gemma 4 31B
0.0
Dtbench
Gemini 3.1 Pro Preview leads by +24.0
Gemini 3.1 Pro Preview
95.1
Gemma 4 31B
71.1
GPQA diamond
Gemini 3.1 Pro Preview leads by +26.0
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 3.1 Pro Preview
96.5
Gemma 4 31B
70.5
Lmca
Gemini 3.1 Pro Preview leads by +17.1
Gemini 3.1 Pro Preview
63.3
Gemma 4 31B
46.2
OTIS Mock AIME 2024-2025
Gemini 3.1 Pro Preview leads by +22.3
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3.1 Pro Preview
95.6
Gemma 4 31B
73.3
SimpleQA Verified
Gemini 3.1 Pro Preview leads by +63.1
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
Gemini 3.1 Pro Preview
73.5
Gemma 4 31B
10.4
WeirdML
Gemini 3.1 Pro Preview leads by +19.8
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Gemini 3.1 Pro Preview
72.1
Gemma 4 31B
52.3
Full benchmark table
| Benchmark | Gemini 3.1 Pro Preview | Gemma 4 31B |
|---|---|---|
Artificial Analysis · CritPt | 17.7 | 1.4 |
Artificial Analysis · GDPval | 14.6 | 6.0 |
Artificial Analysis · GPQA Diamond | 94.1 | 85.7 |
Artificial Analysis · Humanity's Last Exam | 47.0 | 23.6 |
Artificial Analysis · IFBench | 77.1 | 75.6 |
Artificial Analysis · Long Context Reasoning | 82.0 | 69.7 |
Artificial Analysis · MMMU Pro | 82.4 | 73.4 |
Artificial Analysis · Quality Index | 29.7 | 14.7 |
Artificial Analysis · SciCode | 58.7 | 45.5 |
Artificial Analysis · tau2-Bench Telecom | 95.6 | 59.9 |
Artificial Analysis · Terminal-Bench Hard | 53.8 | 36.4 |
Chatbot Arena Elo · Coding | 1446.2 | 1364.7 |
Chatbot Arena Elo · Overall | 1487.0 | 1452.8 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 48.4 | 0.0 |
Dtbench | 95.1 | 71.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 96.5 | 70.5 |
Lmca | 63.3 | 46.2 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 95.6 | 73.3 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 73.5 | 10.4 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 72.1 | 52.3 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.00 | $12.00 | 1.0M tokens (~524 books) | $45.00 | |
| $0.20 | $0.40 | 262K tokens (~131 books) | $2.50 |
Gemini 3.1 Pro Preview vs Gemma 4 31B · questions answered from the data
Gemini 3.1 Pro Preview leads on 20 of 20 shared benchmarks (Artificial Analysis · CritPt, Artificial Analysis · GDPval, Artificial Analysis · GPQA Diamond, Artificial Analysis · Humanity's Last Exam, 16 more), Gemma 4 31B on 0
People also compared