Compare · ModelsLive · 2 picked · head to head
Gemini 3.1 Pro Preview vs GPT-5.4
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 3.1 Pro Preview wins on 10/16 benchmarks
Gemini 3.1 Pro Preview wins 10 of 16 shared benchmarks. Leads in reasoning · arena · knowledge.
Category leads
speed·GPT-5.4agentic·GPT-5.4reasoning·Gemini 3.1 Pro Previewarena·Gemini 3.1 Pro Previewknowledge·Gemini 3.1 Pro Previewmath·GPT-5.4coding·GPT-5.4
Hype vs Reality
Attention vs performance
Gemini 3.1 Pro Preview
#36 by perf·no signal
GPT-5.4
#44 by perf·no signal
Best value
Gemini 3.1 Pro Preview
1.3x better value than GPT-5.4
Gemini 3.1 Pro Preview
8.7 pts/$
$7.00/M
GPT-5.4
6.7 pts/$
$8.75/M
Vendor risk
Who is behind the model
Google DeepMind
$4.00T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
16 benchmarks · 2 models
Gemini 3.1 Pro PreviewGPT-5.4
Artificial Analysis · Agentic Index
GPT-5.4 leads by +10.3
Gemini 3.1 Pro Preview
59.1
GPT-5.4
69.4
Artificial Analysis · Coding Index
GPT-5.4 leads by +1.8
Gemini 3.1 Pro Preview
55.5
GPT-5.4
57.3
Artificial Analysis · Quality Index
Gemini 3.1 Pro Preview leads by +0.0
Gemini 3.1 Pro Preview
57.2
GPT-5.4
57.2
APEX-Agents
GPT-5.4 leads by +2.4
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
Gemini 3.1 Pro Preview
33.5
GPT-5.4
35.9
ARC-AGI
Gemini 3.1 Pro Preview leads by +4.3
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-5.4
93.7
ARC-AGI-2
Gemini 3.1 Pro Preview leads by +3.1
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-5.4
74.0
Chatbot Arena Elo · Overall
Gemini 3.1 Pro Preview leads by +26.8
Gemini 3.1 Pro Preview
1492.6
GPT-5.4
1465.8
Chess Puzzles
Gemini 3.1 Pro Preview leads by +11.0
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
55.0
GPT-5.4
44.0
FrontierMath-2025-02-28-Private
GPT-5.4 leads by +10.7
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
Gemini 3.1 Pro Preview
36.9
GPT-5.4
47.6
FrontierMath-Tier-4-2025-07-01-Private
GPT-5.4 leads by +10.4
FrontierMath Tier 4 (Jul 2025) · the most challenging tier of frontier mathematics, containing problems that push the absolute limits of AI mathematical reasoning.
Gemini 3.1 Pro Preview
16.7
GPT-5.4
27.1
GPQA diamond
Gemini 3.1 Pro Preview leads by +1.1
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
92.1
GPT-5.4
91.1
OTIS Mock AIME 2024-2025
Gemini 3.1 Pro Preview leads by +0.3
OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 3.1 Pro Preview
95.6
GPT-5.4
95.3
PostTrainBench
Gemini 3.1 Pro Preview leads by +1.4
Gemini 3.1 Pro Preview
21.6
GPT-5.4
20.2
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
77.3
GPT-5.4
44.8
SWE-Bench verified
GPT-5.4 leads by +1.2
Gemini 3.1 Pro Preview
75.6
GPT-5.4
76.9
WeirdML
Gemini 3.1 Pro Preview leads by +14.7
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-5.4
57.4
Full benchmark table
| Benchmark | Gemini 3.1 Pro Preview | GPT-5.4 |
|---|---|---|
Artificial Analysis · Agentic Index | 59.1 | 69.4 |
Artificial Analysis · Coding Index | 55.5 | 57.3 |
Artificial Analysis · Quality Index | 57.2 | 57.2 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 33.5 | 35.9 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 98.0 | 93.7 |
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 | 74.0 |
Chatbot Arena Elo · Overall | 1492.6 | 1465.8 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 55.0 | 44.0 |
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. | 36.9 | 47.6 |
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. | 16.7 | 27.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 92.1 | 91.1 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 95.6 | 95.3 |
PostTrainBench | 21.6 | 20.2 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 77.3 | 44.8 |
SWE-Bench verified | 75.6 | 76.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 72.1 | 57.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Gemini 3.1 Pro Preview | $2.00 | $12.00 | 1.0M tokens (~524 books) | $45.00 |
| GPT-5.4 | $2.50 | $15.00 | 1.1M tokens (~525 books) | $56.25 |