Compare · ModelsLive · 2 picked · head to head

GPT-4.1 vs Gemini 1.5 Pro (Feb 2024)

Side by side · benchmarks, pricing, and signals you can act on.

Winner summary

GPT-4.1 wins 10 of 12 shared benchmarks. Leads in coding · knowledge · language.

Category leads
reasoning·Gemini 1.5 Pro (Feb 2024)coding·GPT-4.1knowledge·GPT-4.1language·GPT-4.1math·GPT-4.1
Hype vs Reality
GPT-4.1
#123 by perf·no signal
QUIET
Gemini 1.5 Pro (Feb 2024)
#138 by perf·no signal
QUIET
Best value
GPT-4.1
8.7 pts/$
$5.00/M
Gemini 1.5 Pro (Feb 2024)
no price
Vendor risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Google DeepMind logo
Google DeepMind
$4.00T·Tier 1
Low risk
Head to head
GPT-4.1Gemini 1.5 Pro (Feb 2024)
ARC-AGI-2
Gemini 1.5 Pro (Feb 2024) leads by +0.4
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
GPT-4.1
0.4
Gemini 1.5 Pro (Feb 2024)
0.8
CadEval
GPT-4.1 leads by +8.0
CadEval · evaluates the ability to generate and reason about Computer-Aided Design code, testing spatial reasoning and engineering knowledge.
GPT-4.1
42.0
Gemini 1.5 Pro (Feb 2024)
34.0
GPQA diamond
GPT-4.1 leads by +28.1
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-4.1
55.9
Gemini 1.5 Pro (Feb 2024)
27.8
HELM · GPQA
GPT-4.1 leads by +12.5
GPT-4.1
65.9
Gemini 1.5 Pro (Feb 2024)
53.4
HELM · IFEval
GPT-4.1 leads by +0.1
GPT-4.1
83.8
Gemini 1.5 Pro (Feb 2024)
83.7
HELM · MMLU-Pro
GPT-4.1 leads by +7.4
GPT-4.1
81.1
Gemini 1.5 Pro (Feb 2024)
73.7
HELM · Omni-MATH
GPT-4.1 leads by +10.7
GPT-4.1
47.1
Gemini 1.5 Pro (Feb 2024)
36.4
HELM · WildBench
GPT-4.1 leads by +4.1
GPT-4.1
85.4
Gemini 1.5 Pro (Feb 2024)
81.3
MATH level 5
GPT-4.1 leads by +42.3
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-4.1
83.0
Gemini 1.5 Pro (Feb 2024)
40.8
OTIS Mock AIME 2024-2025
GPT-4.1 leads by +31.6
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4.1
38.3
Gemini 1.5 Pro (Feb 2024)
6.7
SimpleBench
Gemini 1.5 Pro (Feb 2024) leads by +0.1
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-4.1
12.4
Gemini 1.5 Pro (Feb 2024)
12.5
WeirdML
GPT-4.1 leads by +16.8
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-4.1
39.0
Gemini 1.5 Pro (Feb 2024)
22.2
Full benchmark table
BenchmarkGPT-4.1Gemini 1.5 Pro (Feb 2024)
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.
0.40.8
CadEval
CadEval · evaluates the ability to generate and reason about Computer-Aided Design code, testing spatial reasoning and engineering knowledge.
42.034.0
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
55.927.8
HELM · GPQA
65.953.4
HELM · IFEval
83.883.7
HELM · MMLU-Pro
81.173.7
HELM · Omni-MATH
47.136.4
HELM · WildBench
85.481.3
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
83.040.8
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
38.36.7
SimpleBench
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
12.412.5
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
39.022.2
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
OpenAI logoGPT-4.1$2.00$8.001.0M tokens (~524 books)$35.00
Google DeepMind logoGemini 1.5 Pro (Feb 2024)