Compare · ModelsLive · 2 picked · head to head

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

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
Gemini 1.5 Flash (May 2024)
#105 by perf·no signal
QUIET
GPT-4.1 Mini
#118 by perf·no signal
QUIET
Best value
Gemini 1.5 Flash (May 2024)
no price
GPT-4.1 Mini
44.5 pts/$
$1.00/M
Vendor risk
Google DeepMind logo
Google DeepMind
$4.00T·Tier 1
Low risk
OpenAI logo
OpenAI
$840.0B·Tier 1
Medium risk
Head to head
Gemini 1.5 Flash (May 2024)GPT-4.1 Mini
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.
Gemini 1.5 Flash (May 2024)
0.1
GPT-4.1 Mini
4.5
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.
Gemini 1.5 Flash (May 2024)
20.5
GPT-4.1 Mini
54.5
HELM · GPQA
GPT-4.1 Mini leads by +17.7
Gemini 1.5 Flash (May 2024)
43.7
GPT-4.1 Mini
61.4
HELM · IFEval
GPT-4.1 Mini leads by +7.3
Gemini 1.5 Flash (May 2024)
83.1
GPT-4.1 Mini
90.4
HELM · MMLU-Pro
GPT-4.1 Mini leads by +10.5
Gemini 1.5 Flash (May 2024)
67.8
GPT-4.1 Mini
78.3
HELM · Omni-MATH
GPT-4.1 Mini leads by +18.6
Gemini 1.5 Flash (May 2024)
30.5
GPT-4.1 Mini
49.1
HELM · WildBench
GPT-4.1 Mini leads by +4.6
Gemini 1.5 Flash (May 2024)
79.2
GPT-4.1 Mini
83.8
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.
Gemini 1.5 Flash (May 2024)
25.1
GPT-4.1 Mini
87.3
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.
Gemini 1.5 Flash (May 2024)
3.8
GPT-4.1 Mini
44.7
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.
Gemini 1.5 Flash (May 2024)
24.9
GPT-4.1 Mini
37.6
Full benchmark table
BenchmarkGemini 1.5 Flash (May 2024)GPT-4.1 Mini
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.
0.14.5
GPQA diamond
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
20.554.5
HELM · GPQA
43.761.4
HELM · IFEval
83.190.4
HELM · MMLU-Pro
67.878.3
HELM · Omni-MATH
30.549.1
HELM · WildBench
79.283.8
MATH level 5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
25.187.3
OTIS Mock AIME 2024-2025
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
3.844.7
WeirdML
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
24.937.6
Pricing · per 1M tokens · projected $/mo at 10M tokens
ModelInputOutputContextProjected $/mo
Google DeepMind logoGemini 1.5 Flash (May 2024)
OpenAI logoGPT-4.1 Mini$0.40$1.601.0M tokens (~524 books)$7.00