Gemini 2.5 ProvsGPT-4 Turbo
Gemini 2.5 Pro | GPT-4 Turbo | |
|---|---|---|
| Specifications | ||
Context windowHow much text the model can hold in mind at once — your question, any documents you attach, the conversation so far, and its own reply. Go past it and the earliest part falls out of view. | — | 128k |
| API pricingUSD per 1M tokens · lower wins · base tier | ||
Input priceWhat you pay for everything you send the model — your question, plus any documents or earlier conversation you include with it. | $1.25 | $10.00 |
Output priceWhat you pay for the text the model writes back. It is normally the dearer half: producing an answer costs more than reading one. | $10.00 | $30.00 |
Cached input priceA reduced rate for text you send over and over. If every request starts with the same instructions or the same document, the provider keeps a copy ready and charges less to read it again. | $0.125 | — |
| Benchmarks | ||
GPQA DiamondScience — Graduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 86.4% | 42.5% |
| BenchmarksPublished by one model only | ||
BullshitBench v2Nonsense detection — Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 20% | — |
SWE-Bench VerifiedCoding — Real coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 59.6% | — |
MMMUMultimodal — Tests the AI on understanding images and text together across many college subjects. Higher is better. | 68% | — |
Arena Elo (Code)Community preference (code) — Like the text arena, but people vote on which AI writes better code. The votes become a chess-style Elo rating on arena.ai. Higher is better. | 1224 | — |
Arena Elo (Vision)Community preference (vision) — Real people give two anonymous AIs the same image — a photo, a screenshot, a diagram — and vote for whichever reads it better. The votes become a chess-style Elo rating on arena.ai. It measures which AI people find more useful at looking at things, not how it scores on a fixed test set. Higher is better. | 1246 | — |
Arena Elo (Documents)Community preference (documents) — Real people hand two anonymous AIs the same PDF or document and vote for whichever answers better. The votes become a chess-style Elo rating on arena.ai. Unlike a fixed document benchmark, the files are whatever people actually brought along. Higher is better. | 1421 | — |
| Overview | ||
| Company | OpenAI | |
| Release date | Mar 25 2025 | Nov 6 2023 |
| Access | Proprietary | Proprietary |
Other comparisons
Frequently asked questions
Gemini 2.5 Pro leads GPT-4 Turbo on 1 of the 1 benchmark they both report (GPQA Diamond). Gemini 2.5 Pro is cheaper on both input and output: $1.25 vs $10.00 per million input tokens, and $10.00 vs $30.00 per million output tokens. Figures are base-tier rates. GPT-4 Turbo shipped 505 days before Gemini 2.5 Pro, so benchmark comparisons should account for the intervening progress.
Published specifications for these two models are limited — see each model page for the latest details.
On GPQA Diamond, Gemini 2.5 Pro leads at 86.4% vs GPT-4 Turbo at 42.5%.
Gemini 2.5 Pro was released by Google on Mar 25 2025.
GPT-4 Turbo was released by OpenAI on Nov 6 2023.
Gemini 2.5 Pro leads on GPQA Diamond — Gemini 2.5 Pro 86.4% vs GPT-4 Turbo 42.5%.
Gemini 2.5 Pro is cheaper on both input and output: $1.25 vs $10.00 per million input tokens, and $10.00 vs $30.00 per million output tokens. Figures are base-tier rates. Rates are pay-as-you-go API prices verified on August 18, 2026.