Side-by-side comparison · models
Gemini 2.5 Flash vs Gemini 1.5 Flash
What we have checked about each, line by line. Every value shows where it came from and when we last confirmed it.
Models
Gemini 2.5 Flash
Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks.
Models
Gemini 1.5 Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost.
Checked facts
Line by line
| Measure | Gemini 2.5 Flash | Gemini 1.5 Flash |
|---|---|---|
| Input price | $0.300 per million tokens | Not checked yet |
| Output price | $2.50 per million tokens | Not checked yet |
| Price on google-ai-studio | $0.015 per million cached input tokens | Not checked yet |
| Price on google-ai-studio | $0.150 per million input tokens | Not checked yet |
| Price on google-ai-studio | $1.25 per million output tokens | Not checked yet |
| Latest version | google/gemini-2.5-flash | Not checked yet |
| Time to first token (ms) | 21,370 | Not checked yet |
| Time to first token (ms) on google-ai-studio | 950 | Not checked yet |
| Output speed (tokens a second) | 211.3 | Not checked yet |
| Output speed (tokens a second) on google-ai-studio | 75 | Not checked yet |
| Tokens served on OpenRouter in a day | 40.4B (for 10 Nov 2026) | Not checked yet |
| Tool calls on OpenRouter in a day | 374.2K (for 10 Nov 2026) | Not checked yet |
| Artificial Analysis Intelligence Index | 15.5 | Not checked yet |
| LMArena text rating (Elo) | 1,417 | Not checked yet |
| LMArena vision rating (Elo) | 1,235 | Not checked yet |
| Design Arena rating (Elo) | 1,132 | Not checked yet |
| Terminal bench | 17.1% (for 17 June 2025) | Not checked yet |
| Balrog | 33.5% (for 17 June 2025) | Not checked yet |
| Dtbench | 76.5% (for 17 June 2025) | Not checked yet |
| Frontiermath 2025 02 28 private | 4.8% (for 17 June 2025) | Not checked yet |
| Frontiermath tier 4 2025 07 01 private | 4.2% (for 17 June 2025) | Not checked yet |
| Lmca | 27.5% (for 17 June 2025) | Not checked yet |
| Simplebench | 41.2% (for 17 June 2025) | Not checked yet |
A line appears only when at least one record has a value we confirmed from a source. Values we have not confirmed are left out, never guessed. Records of different types share fewer lines.
Add a third
Compare with one more record
How this works
Share it, or build your own
This page works for any two or three records in the directory, of any type. The link stays the same whichever order you name them in, so you can share it as it is. Change the records in the address, for example /directories/vs/claude-code-vs-cursor, or start from our editorial comparisons.