Compare · ModelsLive · 2 picked · head to head
Gemini 2.0 Flash vs GPT-4o-mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 2.0 Flash wins on 8/9 benchmarks
Gemini 2.0 Flash wins 8 of 9 shared benchmarks. Leads in coding · reasoning · knowledge.
Category leads
coding·Gemini 2.0 Flashreasoning·Gemini 2.0 Flashknowledge·Gemini 2.0 Flashmath·Gemini 2.0 Flash
Hype vs Reality
Attention vs performance
Gemini 2.0 Flash
#99 by perf·no signal
GPT-4o-mini
#144 by perf·no signal
Best value
Gemini 2.0 Flash
1.8x better value than GPT-4o-mini
Gemini 2.0 Flash
192.0 pts/$
$0.25/M
GPT-4o-mini
105.6 pts/$
$0.38/M
Vendor risk
Who is behind the model
Google DeepMind
$4.00T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
9 benchmarks · 2 models
Gemini 2.0 FlashGPT-4o-mini
Aider polyglot
Gemini 2.0 Flash leads by +34.6
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
Gemini 2.0 Flash
38.2
GPT-4o-mini
3.6
ARC-AGI-2
Gemini 2.0 Flash leads by +1.2
ARC-AGI-2 · the second iteration of the Abstraction and Reasoning Corpus, testing novel pattern recognition and abstract reasoning without prior training data.
Gemini 2.0 Flash
1.3
GPT-4o-mini
0.1
GeoBench
Gemini 2.0 Flash leads by +13.0
GeoBench · tests geographic knowledge and spatial reasoning across countries, landmarks, coordinates, and geopolitical understanding.
Gemini 2.0 Flash
77.0
GPT-4o-mini
64.0
GPQA diamond
Gemini 2.0 Flash leads by +35.2
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 2.0 Flash
52.2
GPT-4o-mini
17.0
Lech Mazur Writing
Gemini 2.0 Flash leads by +4.3
Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication.
Gemini 2.0 Flash
71.5
GPT-4o-mini
67.2
MATH level 5
Gemini 2.0 Flash leads by +29.5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Gemini 2.0 Flash
82.2
GPT-4o-mini
52.6
MMLU
GPT-4o-mini leads by +2.8
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Gemini 2.0 Flash
72.9
GPT-4o-mini
75.7
OTIS Mock AIME 2024-2025
Gemini 2.0 Flash leads by +24.2
OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 2.0 Flash
31.0
GPT-4o-mini
6.8
WeirdML
Gemini 2.0 Flash leads by +14.0
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
Gemini 2.0 Flash
25.8
GPT-4o-mini
11.8
Full benchmark table
| Benchmark | Gemini 2.0 Flash | GPT-4o-mini |
|---|---|---|
Aider polyglot Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework. | 38.2 | 3.6 |
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. | 1.3 | 0.1 |
GeoBench GeoBench · tests geographic knowledge and spatial reasoning across countries, landmarks, coordinates, and geopolitical understanding. | 77.0 | 64.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 52.2 | 17.0 |
Lech Mazur Writing Lech Mazur Writing · evaluates creative writing ability, assessing prose quality, narrative coherence, and stylistic sophistication. | 71.5 | 67.2 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 82.2 | 52.6 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 72.9 | 75.7 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024–2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 31.0 | 6.8 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 25.8 | 11.8 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| Gemini 2.0 Flash | $0.10 | $0.40 | 1.0M tokens (~524 books) | $1.75 |
| GPT-4o-mini | $0.15 | $0.60 | 128K tokens (~64 books) | $2.62 |
People also compared