Compare · ModelsLive · 2 picked · head to head

GPT-4.1 Mini vs Gemini 1.5 Flash (May 2024)

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

Winner summary

GPT-4.1 Mini wins 10 of 10 shared benchmarks. Leads in math · knowledge · language.

Category leads
math·GPT-4.1 Miniknowledge·GPT-4.1 Minilanguage·GPT-4.1 Minireasoning·GPT-4.1 Minicoding·GPT-4.1 Mini
Hype vs Reality
GPT-4.1 Mini
#118 by perf·no signal
QUIET
Gemini 1.5 Flash (May 2024)
#105 by perf·no signal
QUIET
Best value
GPT-4.1 Mini
44.5 pts/$
$1.00/M
Gemini 1.5 Flash (May 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-4.1 MiniGemini 1.5 Flash (May 2024)
FrontierMath-2025-02-28-Private
GPT-4.1 Mini leads by +4.4
FrontierMath (Feb 2025) · original research-level math problems created by mathematicians, testing capabilities at the boundary of current AI mathematical reasoning.
GPT-4.1 Mini
4.5
Gemini 1.5 Flash (May 2024)
0.1
GPQA diamond
GPT-4.1 Mini leads by +34.0
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 Mini
54.5
Gemini 1.5 Flash (May 2024)
20.5
HELM · GPQA
GPT-4.1 Mini leads by +17.7
GPT-4.1 Mini
61.4
Gemini 1.5 Flash (May 2024)
43.7
HELM · IFEval
GPT-4.1 Mini leads by +7.3
GPT-4.1 Mini
90.4
Gemini 1.5 Flash (May 2024)
83.1
HELM · MMLU-Pro
GPT-4.1 Mini leads by +10.5
GPT-4.1 Mini
78.3
Gemini 1.5 Flash (May 2024)
67.8
HELM · Omni-MATH
GPT-4.1 Mini leads by +18.6
GPT-4.1 Mini
49.1
Gemini 1.5 Flash (May 2024)
30.5
HELM · WildBench
GPT-4.1 Mini leads by +4.6
GPT-4.1 Mini
83.8
Gemini 1.5 Flash (May 2024)
79.2
MATH level 5
GPT-4.1 Mini leads by +62.2
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-4.1 Mini
87.3
Gemini 1.5 Flash (May 2024)
25.1
OTIS Mock AIME 2024-2025
GPT-4.1 Mini leads by +40.9
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4.1 Mini
44.7
Gemini 1.5 Flash (May 2024)
3.8
WeirdML
GPT-4.1 Mini leads by +12.7
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
GPT-4.1 Mini
37.6
Gemini 1.5 Flash (May 2024)
24.9
Full benchmark table
BenchmarkGPT-4.1 MiniGemini 1.5 Flash (May 2024)
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.
4.50.1
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
54.520.5
HELM · GPQA
61.443.7
HELM · IFEval
90.483.1
HELM · MMLU-Pro
78.367.8
HELM · Omni-MATH
49.130.5
HELM · WildBench
83.879.2
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
87.325.1
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
44.73.8
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
37.624.9
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
OpenAI logoGPT-4.1 Mini$0.40$1.601.0M tokens (~524 books)$7.00
Google DeepMind logoGemini 1.5 Flash (May 2024)