Gemini 2.5 Pro Preview (May' 25)
May 2025
Gemini 2.5 Pro Preview (May' 25)Compare inon
Benchmarks of Gemini 2.5 Pro Preview (May' 25)6
BenchmarkByScoreRank
Overall1
Science1
Multimodal1
Legacy · saturated or no longer reported3
No benchmark matches
—per task?
not available via APIprice
—output speed?
1Mcontext
Rankingin thinking mode?
Strong at
Alternatives?
ModelScoreCostPer taskWhat changes
BetterGPT-5.6 Lunamedium+4%—$0.016
OpenKimi K3max+14%—$2.00Sampling parameters are fixed+3
BetterMiMo v2.5thinkingOpen+3%—$0.019BetterMiMo v2.5 ProthinkingOpen+5%—$0.054
BetterHy3thinkingOpen+9%—$0.072Context: 1M → 256KModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
GPT-5.6 Lunamedium+4%—$0.016MiMo v2.5thinkingOpen+3%—$0.019MiMo v2.5 ProthinkingOpen+5%—$0.054Hy3thinkingOpen+9%—$0.072Context: 1M → 256KTInkling SmallthinkingOpen+9%—$0.089Context: 1M → 256KModelScoreCostPer taskWhat changes
Kimi K3maxOpen+14%—$2.00Sampling parameters are fixed+3
Qwen3.8 2.4T A95BthinkingOpen+14%—$2.16Context: 1M → 262K+5
MiniMax M3thinkingOpen+13%—$0.51Context: 1M → 524K+1
DeepSeek V4 Pro 0813maxOpen+13%—$0.67Pass back reasoning_content · Chat Completions+4Qwen3.8 FlashthinkingOpen+12%—$0.37Context: 1M → 262K+6ModelScoreCostPer taskWhat changes
Gemini 3.1 Pro Previewthinking+14%—$1.30Cannot use both thinking controlsGemini 3.8 Flashmedium+14%—*$0.93Sampling parameters are ignored+1Gemini 3.6 Flashhigh+13%—*$1.60Gemma 4 31BthinkingOpen+4%—$0.10 / $0.34Context: 1M → 256KGemini 2.5 Prothinking+3%—$0.33Gemini 3.5 Flash Litehigh+2%—$0.19Gemini 3.1 Flash Litehighsame—$0.06Gemini 3 Flash Previewnon-thinking-1%—$0.50 / $3All Google models →History
6 versionsBenchmarks
all categoriesChat & Knowledge
Humanity's Last Exam19.9#124
AA Intelligence Index 4.3.2≈14.5#149
GPQA Diamond82.2#104
Coding
FAQ
How much does Gemini 2.5 Pro Preview (May' 25) cost?›
There is no per-unit API price: not available via API.
Is Gemini 2.5 Pro Preview (May' 25) free to use?›
There is no free API.
How good is Gemini 2.5 Pro Preview (May' 25), and what is it best at?›
#124 of 334 in Chat & Knowledge, #24 of 152 in Coding, #5 of 41 in Vision & Documents.
Is Gemini 2.5 Pro Preview (May' 25) better than Gemini 3.1 Flash Lite?›
On GPQA Diamond, Gemini 2.5 Pro Preview (May' 25) scores 82.2 vs 82.2 — about the same.
What is the context window of Gemini 2.5 Pro Preview (May' 25)?›
1M tokens.
When was Gemini 2.5 Pro Preview (May' 25) released? Is there a newer version?›
Released 2025-05-06. It has been superseded by Gemini 2.5 Pro.
Is Gemini 2.5 Pro Preview (May' 25) open source?›
No, Gemini 2.5 Pro Preview (May' 25) is a closed model available through an API. The closest open-weights option here is Kimi K3.
Can Gemini 2.5 Pro Preview (May' 25) read images?›
It accepts text and audio, video as input.
What is Gemini 2.5 Pro Preview (May' 25)?›
Gemini 2.5 Pro Preview (May' 25) is a closed language model from Google, released May 2025.
What are the best alternatives to Gemini 2.5 Pro Preview (May' 25)?›
GPT-5.6 Luna (better), Kimi K3 (open weights).