Compare · ModelsLive · 2 picked · head to head
GPT-5 vs o1
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-5 wins on 20/20 benchmarks
GPT-5 wins 20 of 20 shared benchmarks. Leads in coding · agentic · reasoning.
Category leads
coding·GPT-5agentic·GPT-5reasoning·GPT-5knowledge·GPT-5general·GPT-5math·GPT-5
Hype vs Reality
Attention vs performance
GPT-5
#116 by perf·#9 by attention
o1
#171 by perf·no signal
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
20 benchmarks · 2 models
GPT-5o1
Aider polyglot
GPT-5 leads by +26.3
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
GPT-5
88.0
o1
61.7
APEX-Agents
GPT-5 leads by +17.2
APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments.
GPT-5
18.3
o1
1.1
ARC-AGI
GPT-5 leads by +35.0
ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization.
GPT-5
65.7
o1
30.7
Chess Puzzles
GPT-5 leads by +30.6
Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities.
GPT-5
37.0
o1
6.4
Dtbench
GPT-5 leads by +26.7
GPT-5
84.5
o1
57.8
Fiction.LiveBench
GPT-5 leads by +13.9
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
GPT-5
97.2
o1
83.3
FrontierMath-2025-02-28-Private
GPT-5 leads by +23.1
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
GPT-5
32.4
o1
9.3
FrontierMath-Tiers-1-3-v2-Private
GPT-5 leads by +42.9
GPT-5
58.4
o1
15.5
GeoBench
GPT-5 leads by +1.0
GeoBench · tests geographic knowledge and spatial reasoning across countries, landmarks, coordinates, and geopolitical understanding.
GPT-5
81.0
o1
80.0
GPQA diamond
GPT-5 leads by +13.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-5
85.0
o1
71.9
HLE
GPT-5 leads by +18.2
HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation.
GPT-5
21.6
o1
3.3
Lech Mazur Writing
GPT-5 leads by +15.8
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
GPT-5
86.0
o1
70.2
Lmca
GPT-5 leads by +20.8
GPT-5
47.0
o1
26.2
MATH level 5
GPT-5 leads by +3.4
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-5
98.1
o1
94.7
Metr Time Horizons
GPT-5 leads by +18.6
GPT-5
69.6
o1
51.0
OTIS Mock AIME 2024-2025
GPT-5 leads by +18.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-5
91.4
o1
73.3
SimpleBench
GPT-5 leads by +19.9
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-5
48.0
o1
28.1
SimpleQA Verified
GPT-5 leads by +9.5
SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information.
GPT-5
50.6
o1
41.1
VPCT
GPT-5 leads by +43.5
VPCT (Visual Pattern Completion Test) · tests visual reasoning and pattern recognition by having models complete visual sequences and transformations.
GPT-5
49.0
o1
5.5
WeirdML
GPT-5 leads by +16.9
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-5
60.7
o1
43.8
Full benchmark table
| Benchmark | GPT-5 | o1 |
|---|---|---|
Aider polyglot Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework. | 88.0 | 61.7 |
APEX-Agents APEX-Agents · evaluates AI agents on complex, multi-step tasks requiring planning, tool use, and autonomous decision-making in realistic environments. | 18.3 | 1.1 |
ARC-AGI ARC-AGI · the original Abstraction and Reasoning Corpus, testing whether AI can solve novel visual pattern recognition tasks without memorization. | 65.7 | 30.7 |
Chess Puzzles Chess Puzzles · tests strategic and tactical reasoning by having models solve chess puzzle positions, evaluating lookahead and pattern recognition abilities. | 37.0 | 6.4 |
Dtbench | 84.5 | 57.8 |
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 97.2 | 83.3 |
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. | 32.4 | 9.3 |
FrontierMath-Tiers-1-3-v2-Private | 58.4 | 15.5 |
GeoBench GeoBench · tests geographic knowledge and spatial reasoning across countries, landmarks, coordinates, and geopolitical understanding. | 81.0 | 80.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 85.0 | 71.9 |
HLE HLE (Humanity's Last Exam) · a reasoning benchmark designed to be the hardest public evaluation of AI. Questions span mathematics, physics, philosophy, and logic · curated to be at or beyond the frontier of human expert capability. Tested with and without tool augmentation. | 21.6 | 3.3 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 86.0 | 70.2 |
Lmca | 47.0 | 26.2 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 98.1 | 94.7 |
Metr Time Horizons | 69.6 | 51.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 91.4 | 73.3 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 48.0 | 28.1 |
SimpleQA Verified SimpleQA Verified · short factual questions with verified answers, measuring factual accuracy and the tendency to hallucinate or provide incorrect information. | 50.6 | 41.1 |
VPCT VPCT (Visual Pattern Completion Test) · tests visual reasoning and pattern recognition by having models complete visual sequences and transformations. | 49.0 | 5.5 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 60.7 | 43.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens