Compare · ModelsLive · 2 picked · head to head
Gemini 2.5 Pro vs GPT-4o (2024-05-13)
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
Gemini 2.5 Pro wins on 5/5 benchmarks
Gemini 2.5 Pro wins 5 of 5 shared benchmarks. Leads in arena · knowledge · math.
Category leads
arena·Gemini 2.5 Proknowledge·Gemini 2.5 Promath·Gemini 2.5 Pro
Hype vs Reality
Attention vs performance
Gemini 2.5 Pro
#116 by perf·no signal
GPT-4o (2024-05-13)
#110 by perf·no signal
Best value
Gemini 2.5 Pro
1.8x better value than GPT-4o (2024-05-13)
Gemini 2.5 Pro
9.0 pts/$
$5.63/M
GPT-4o (2024-05-13)
5.1 pts/$
$10.00/M
Vendor risk
Who is behind the model
Google DeepMind
$4.20T·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
5 benchmarks · 2 models
Gemini 2.5 ProGPT-4o (2024-05-13)
Chatbot Arena Elo · Overall
Gemini 2.5 Pro leads by +99.5
Gemini 2.5 Pro
1445.6
GPT-4o (2024-05-13)
1346.1
Balrog
Gemini 2.5 Pro leads by +11.0
Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning.
Gemini 2.5 Pro
43.3
GPT-4o (2024-05-13)
32.3
GPQA diamond
Gemini 2.5 Pro leads by +48.5
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
Gemini 2.5 Pro
80.4
GPT-4o (2024-05-13)
31.9
MATH level 5
Gemini 2.5 Pro leads by +44.5
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
Gemini 2.5 Pro
95.6
GPT-4o (2024-05-13)
51.0
OTIS Mock AIME 2024-2025
Gemini 2.5 Pro leads by +78.5
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
Gemini 2.5 Pro
84.7
GPT-4o (2024-05-13)
6.2
Full benchmark table
| Benchmark | Gemini 2.5 Pro | GPT-4o (2024-05-13) |
|---|---|---|
Chatbot Arena Elo · Overall | 1445.6 | 1346.1 |
Balrog Balrog · benchmarks AI agents on text-based adventure games, testing language understanding, strategic planning, and long-horizon reasoning. | 43.3 | 32.3 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 80.4 | 31.9 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 95.6 | 51.0 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 84.7 | 6.2 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $1.25 | $10.00 | 1.0M tokens (~524 books) | $34.38 | |
| $5.00 | $15.00 | 128K tokens (~64 books) | $75.00 |