AI Models · Compare
Gemini 2.5 Pro vs Gemini 1.5 Pro
Side-by-side intelligence, speed, price, benchmarks, strengths and weaknesses for Gemini 2.5 Pro and Gemini 1.5 Pro — refreshed monthly.
Want to compare different models?
Pick any two modelsGoogle
Gemini 2.5 Pro
ProprietarySep 2025
2M-token context + native multimodality — unbeatable for huge docs.
Google
Gemini 1.5 Pro
ProprietaryMay 2024
The original 2M-context model — still useful for legacy pipelines.
Head to head
Spec
Gemini 2.5 Pro
Gemini 1.5 Pro
Intelligence index↑ better
Winner78
67
Speed↑ better
Winner110 tok/s
60 tok/s
Time to first token↓ better
Winner0.7 s
0.9 s
Context window↑ better
2M
2M
Max output↑ better
Winner66k
8k
Input price↓ better
$1.25 / 1M tokens
$1.25 / 1M tokens
Output price↓ better
$5.00 / 1M tokens
$5.00 / 1M tokens
Blended price↓ better
$2.19 / 1M tokens
$2.19 / 1M tokens
License
Proprietary
Proprietary
Input modalities
text, image, audio, video
text, image, audio, video
Output modalities
text
text
Benchmark showdown
MMLU
Gemini 2.5 Pro
89.5
Gemini 1.5 Pro
85.9
MMLU Pro
Gemini 2.5 Pro
78.5
Gemini 1.5 Pro
69.0
GPQA
Gemini 2.5 Pro
66.0
Gemini 1.5 Pro
50.6
MATH
Gemini 2.5 Pro
91.0
Gemini 1.5 Pro
80.0
HumanEval
Gemini 2.5 Pro
91.5
Gemini 1.5 Pro
84.0
Strengths, weaknesses and best-for
Gemini 2.5 Pro
Strengths
- 2M context
- Native video understanding
- Strong on math
Weaknesses
- Output ceiling lower than competitors
Best for
- Whole-codebase analysis
- Long-doc workflows
- Video QA
Gemini 1.5 Pro
Strengths
- 2M context
- Stable API
Weaknesses
- Superseded by 2.5 Pro at the same price
Best for
- Existing 1.5 deployments
- Document QA
Quick verdict
- Pick Gemini 2.5 Pro if you want it smarter and faster.
Auto-generated from the spec sheet. Always validate on your own evals.
More popular AI model comparisons
One-click matchups for the comparisons people search the most.
Build the shortlist that fits your stack
Open every model in one place — sortable table with intelligence, speed and price.