Compare · ModelsLive · 2 picked · head to head
GPT-4o (2024-08-06) vs Gemini 1.5 Pro (May 2024)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 1.5 Pro (May 2024) wins on 4/6 benchmarks
Gemini 1.5 Pro (May 2024) wins 4 of 6 shared benchmarks. Leads in coding · reasoning.
Category leads
coding·Gemini 1.5 Pro (May 2024)knowledge·GPT-4o (2024-08-06)math·GPT-4o (2024-08-06)reasoning·Gemini 1.5 Pro (May 2024)
Hype vs Reality
Attention vs performance
GPT-4o (2024-08-06)
#195 by perf·no signal
Gemini 1.5 Pro (May 2024)
#165 by perf·no signal
Best value
GPT-4o (2024-08-06)
GPT-4o (2024-08-06)
5.7 pts/$
$6.25/M
Gemini 1.5 Pro (May 2024)
—
no price
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Google DeepMind
$4.00T·Tier 1
Head to head
6 benchmarks · 2 models
GPT-4o (2024-08-06)Gemini 1.5 Pro (May 2024)
CadEval
Gemini 1.5 Pro (May 2024) leads by +8.0
CadEval · evaluates the ability to generate and reason about Computer-Aided Design code, testing spatial reasoning and engineering knowledge.
GPT-4o (2024-08-06)
26.0
Gemini 1.5 Pro (May 2024)
34.0
GPQA diamond
GPT-4o (2024-08-06) leads by +4.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-4o (2024-08-06)
32.3
Gemini 1.5 Pro (May 2024)
27.8
MATH level 5
GPT-4o (2024-08-06) leads by +12.5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-4o (2024-08-06)
53.3
Gemini 1.5 Pro (May 2024)
40.8
MMLU
Gemini 1.5 Pro (May 2024) leads by +2.1
Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge.
GPT-4o (2024-08-06)
79.1
Gemini 1.5 Pro (May 2024)
81.2
OTIS Mock AIME 2024-2025
Gemini 1.5 Pro (May 2024) leads by +0.4
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4o (2024-08-06)
6.3
Gemini 1.5 Pro (May 2024)
6.7
SimpleBench
Gemini 1.5 Pro (May 2024) leads by +11.2
SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking.
GPT-4o (2024-08-06)
1.4
Gemini 1.5 Pro (May 2024)
12.5
Full benchmark table
| Benchmark | GPT-4o (2024-08-06) | Gemini 1.5 Pro (May 2024) |
|---|---|---|
CadEval CadEval · evaluates the ability to generate and reason about Computer-Aided Design code, testing spatial reasoning and engineering knowledge. | 26.0 | 34.0 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 32.3 | 27.8 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 53.3 | 40.8 |
MMLU Massive Multitask Language Understanding · 57 subjects spanning STEM, humanities, social sciences, and more. The standard benchmark for broad knowledge. | 79.1 | 81.2 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 6.3 | 6.7 |
SimpleBench SimpleBench · tests fundamental reasoning capabilities with straightforward problems designed to expose gaps in basic logical and spatial thinking. | 1.4 | 12.5 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $2.50 | $10.00 | 128K tokens (~64 books) | $43.75 | |
| — | — | — | — |