Compare · ModelsLive · 2 picked · head to head
Gemini 3.1 Pro Preview vs GPT-5.6 Luna
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.1 Pro Preview wins on 11/17 benchmarks
Gemini 3.1 Pro Preview wins 11 of 17 shared benchmarks. Leads in reasoning · knowledge · general.
Category leads
reasoning·Gemini 3.1 Pro Previewknowledge·Gemini 3.1 Pro Previewcoding·GPT-5.6 Lunageneral·Gemini 3.1 Pro Previewmath·GPT-5.6 Luna
Hype vs Reality
Attention vs performance
Gemini 3.1 Pro Preview
#137 by perf·#5 by attention
GPT-5.6 Luna
#59 by perf·#4 by attention
Best value
GPT-5.6 Luna
12.0x better value than Gemini 3.1 Pro Preview
Gemini 3.1 Pro Preview
6.9 pts/$
$7.00/M
GPT-5.6 Luna
82.4 pts/$
$0.70/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
17 benchmarks · 2 models
Gemini 3.1 Pro PreviewGPT-5.6 Luna
ARC-AGI
Gemini 3.1 Pro Preview leads by +10.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
Gemini 3.1 Pro Preview
98.0
GPT-5.6 Luna
88.0
ARC-AGI-2
Gemini 3.1 Pro Preview leads by +17.6
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Gemini 3.1 Pro Preview
77.1
GPT-5.6 Luna
59.5
Balrog
Gemini 3.1 Pro Preview leads by +11.4
Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning.
Gemini 3.1 Pro Preview
57.0
GPT-5.6 Luna
45.6
Chess Puzzles
Gemini 3.1 Pro Preview leads by +15.8
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
52.6
GPT-5.6 Luna
36.9
Deepswe
GPT-5.6 Luna leads by +55.5
Gemini 3.1 Pro Preview
11.7
GPT-5.6 Luna
67.2
Dtbench
Gemini 3.1 Pro Preview leads by +13.3
Gemini 3.1 Pro Preview
95.1
GPT-5.6 Luna
81.8
FrontierMath-Tier-4-v2-Private
GPT-5.6 Luna leads by +34.1
Gemini 3.1 Pro Preview
26.8
GPT-5.6 Luna
61.0
FrontierMath-Tiers-1-3-v2-Private
GPT-5.6 Luna leads by +22.5
Gemini 3.1 Pro Preview
59.6
GPT-5.6 Luna
82.1
Furniture Assembly
GPT-5.6 Luna leads by +17.9
Gemini 3.1 Pro Preview
0.0
GPT-5.6 Luna
17.9
GPQA diamond
Gemini 3.1 Pro Preview leads by +3.8
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
92.6
GPT-5.6 Luna
88.8
Lmca
Gemini 3.1 Pro Preview leads by +6.2
Gemini 3.1 Pro Preview
63.3
GPT-5.6 Luna
57.1
Mystery Game Puzzles
Gemini 3.1 Pro Preview leads by +14.3
Gemini 3.1 Pro Preview
27.3
GPT-5.6 Luna
13.0
OTIS Mock AIME 2024-2025
GPT-5.6 Luna leads by +2.7
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3.1 Pro Preview
95.6
GPT-5.6 Luna
98.3
Proofbench
GPT-5.6 Luna leads by +34.0
Gemini 3.1 Pro Preview
26.0
GPT-5.6 Luna
60.0
SimpleBench
Gemini 3.1 Pro Preview leads by +39.4
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
Gemini 3.1 Pro Preview
75.5
GPT-5.6 Luna
36.2
SimpleQA Verified
Gemini 3.1 Pro Preview leads by +32.5
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
GPT-5.6 Luna
41.0
WeirdML
Gemini 3.1 Pro Preview leads by +11.2
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
GPT-5.6 Luna
60.9
Full benchmark table
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.6 Luna |
|---|---|---|
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 98.0 | 88.0 |
ARC-AGI-2 ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data. | 77.1 | 59.5 |
Balrog Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning. | 57.0 | 45.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 52.6 | 36.9 |
Deepswe | 11.7 | 67.2 |
Dtbench | 95.1 | 81.8 |
FrontierMath-Tier-4-v2-Private | 26.8 | 61.0 |
FrontierMath-Tiers-1-3-v2-Private | 59.6 | 82.1 |
Furniture Assembly | 0.0 | 17.9 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 92.6 | 88.8 |
Lmca | 63.3 | 57.1 |
Mystery Game Puzzles | 27.3 | 13.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 95.6 | 98.3 |
Proofbench | 26.0 | 60.0 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 75.5 | 36.2 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 73.5 | 41.0 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 72.1 | 60.9 |
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 | $1.20 | 1.1M tokens (~525 books) | $4.50 |