Compare · ModelsLive · 2 picked · head to head
Gemini 1.5 Flash (May 2024) vs GPT-4 Turbo
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 1.5 Flash (May 2024) wins on 4/7 benchmarks
Gemini 1.5 Flash (May 2024) wins 4 of 7 shared benchmarks. Leads in knowledge · math · coding.
Category leads
general·GPT-4 Turboknowledge·Gemini 1.5 Flash (May 2024)math·Gemini 1.5 Flash (May 2024)coding·Gemini 1.5 Flash (May 2024)
Hype vs Reality
Attention vs performance
Gemini 1.5 Flash (May 2024)
#165 by perf·no signal
GPT-4 Turbo
#204 by perf·no signal
Best value
GPT-4 Turbo
Gemini 1.5 Flash (May 2024)
n/a
no price
GPT-4 Turbo
2.0 pts/$
$20.00/M
Vendor risk
Who is behind the model
Google DeepMind
$3.53T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
7 benchmarks · 2 models
Gemini 1.5 Flash (May 2024)GPT-4 Turbo
Dtbench
GPT-4 Turbo leads by +18.8
Gemini 1.5 Flash (May 2024)
19.0
GPT-4 Turbo
37.8
GPQA diamond
Gemini 1.5 Flash (May 2024) leads by +13.5
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)
21.4
GPT-4 Turbo
7.8
GSM8K
GPT-4 Turbo leads by +7.6
Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve.
Gemini 1.5 Flash (May 2024)
82.4
GPT-4 Turbo
90.0
MATH level 5
Gemini 1.5 Flash (May 2024) leads by +2.2
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 Turbo
23.0
MMLU
GPT-4 Turbo leads by +6.0
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
Gemini 1.5 Flash (May 2024)
70.5
GPT-4 Turbo
76.5
OTIS Mock AIME 2024-2025
Gemini 1.5 Flash (May 2024) leads by +2.8
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 Turbo
1.0
WeirdML
Gemini 1.5 Flash (May 2024) leads by +12.5
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 Turbo
12.4
Full benchmark table
| Benchmark | Gemini 1.5 Flash (May 2024) | GPT-4 Turbo |
|---|---|---|
Dtbench | 19.0 | 37.8 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 21.4 | 7.8 |
GSM8K Grade School Math 8K · 8,500 linguistically diverse grade-school math word problems that require multi-step reasoning to solve. | 82.4 | 90.0 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 25.1 | 23.0 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 70.5 | 76.5 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 3.8 | 1.0 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 24.9 | 12.4 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| n/a | n/a | n/a | n/a | |
| $10.00 | $30.00 | 128K tokens (~64 books) | $150.00 |