Compare · ModelsLive · 2 picked · head to head
GPT-5.2 vs Gemini 3.1 Pro Preview
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.1 Pro Preview wins on 11/16 benchmarks
Gemini 3.1 Pro Preview wins 11 of 16 shared benchmarks. Leads in reasoning · arena · knowledge.
Category leads
agentic·GPT-5.2reasoning·Gemini 3.1 Pro Previewarena·Gemini 3.1 Pro Previewknowledge·Gemini 3.1 Pro Previewmath·GPT-5.2coding·Gemini 3.1 Pro Preview
Hype vs Reality
Attention vs performance
GPT-5.2
#74 by perf·no signal
Gemini 3.1 Pro Preview
#36 by perf·no signal
Best value
Gemini 3.1 Pro Preview
1.3x better value than GPT-5.2
GPT-5.2
6.9 pts/$
$7.88/M
Gemini 3.1 Pro Preview
8.7 pts/$
$7.00/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Google DeepMind
$4.00T·Tier 1
Head to head
16 benchmarks · 2 models
GPT-5.2Gemini 3.1 Pro Preview
APEX-Agents
GPT-5.2 leads by +0.8
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-5.2
34.3
Gemini 3.1 Pro Preview
33.5
ARC-AGI
Gemini 3.1 Pro Preview leads by +11.8
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-5.2
86.2
Gemini 3.1 Pro Preview
98.0
ARC-AGI-2
Gemini 3.1 Pro Preview leads by +24.2
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-5.2
52.9
Gemini 3.1 Pro Preview
77.1
Chatbot Arena Elo · Coding
Gemini 3.1 Pro Preview leads by +52.6
GPT-5.2
1403.1
Gemini 3.1 Pro Preview
1455.7
Chatbot Arena Elo · Overall
Gemini 3.1 Pro Preview leads by +53.1
GPT-5.2
1439.5
Gemini 3.1 Pro Preview
1492.6
Chess Puzzles
Gemini 3.1 Pro Preview leads by +6.0
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-5.2
49.0
Gemini 3.1 Pro Preview
55.0
FrontierMath-2025-02-28-Private
GPT-5.2 leads by +3.8
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
GPT-5.2
40.7
Gemini 3.1 Pro Preview
36.9
FrontierMath-Tier-4-2025-07-01-Private
GPT-5.2 leads by +2.1
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
GPT-5.2
18.8
Gemini 3.1 Pro Preview
16.7
GPQA diamond
Gemini 3.1 Pro Preview leads by +3.6
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5.2
88.5
Gemini 3.1 Pro Preview
92.1
OTIS Mock AIME 2024-2025
GPT-5.2 leads by +0.5
OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5.2
96.1
Gemini 3.1 Pro Preview
95.6
PostTrainBench
Gemini 3.1 Pro Preview leads by +0.2
GPT-5.2
21.4
Gemini 3.1 Pro Preview
21.6
SimpleBench
Gemini 3.1 Pro Preview leads by +40.6
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-5.2
35.0
Gemini 3.1 Pro Preview
75.5
SimpleQA Verified
Gemini 3.1 Pro Preview leads by +38.4
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-5.2
38.9
Gemini 3.1 Pro Preview
77.3
SWE-Bench verified
Gemini 3.1 Pro Preview leads by +1.9
GPT-5.2
73.8
Gemini 3.1 Pro Preview
75.6
Terminal Bench
Gemini 3.1 Pro Preview leads by +13.5
Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency.
GPT-5.2
64.9
Gemini 3.1 Pro Preview
78.4
WeirdML
GPT-5.2 leads by +0.1
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5.2
72.2
Gemini 3.1 Pro Preview
72.1
Full benchmark table
| Benchmark | GPT-5.2 | Gemini 3.1 Pro Preview |
|---|---|---|
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 34.3 | 33.5 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 86.2 | 98.0 |
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. | 52.9 | 77.1 |
Chatbot Arena Elo · Coding | 1403.1 | 1455.7 |
Chatbot Arena Elo · Overall | 1439.5 | 1492.6 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 49.0 | 55.0 |
FrontierMath-2025-02-28-Private FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning. | 40.7 | 36.9 |
FrontierMath-Tier-4-2025-07-01-Private FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning. | 18.8 | 16.7 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 88.5 | 92.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 96.1 | 95.6 |
PostTrainBench | 21.4 | 21.6 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 35.0 | 75.5 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 38.9 | 77.3 |
SWE-Bench verified | 73.8 | 75.6 |
Terminal Bench Terminal Bench · tests the ability to accomplish real-world tasks using terminal commands, evaluating shell scripting and CLI tool proficiency. | 64.9 | 78.4 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 72.2 | 72.1 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| GPT-5.2 | $1.75 | $14.00 | 400K tokens (~200 books) | $48.13 |
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 1.0M tokens (~524 books) | $45.00 |
People also compared