whatmodel.sh / Gemini 2.5 Flash-Lite
Gemini 2.5 Flash-Lite
↗ share
+ contribute
Gemini 2.5 Flash-Lite is a closed-weights language model from Google, released July 2025.
Catalogue identity notes
Release month: Gemini API changelog, July 22, 2025: 'Released gemini-2.5-flash-lite, our fast, low-cost, high-performance Gemini 2.5 model.'
Model information sources
$ how it compares
The LLMs ranked either side of Gemini 2.5 Flash-Lite, out of 828 with a score, then more from Google.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 277 |  Command A (03-2025) | 57±1 | api $4.38/M +local | ||
| 278 |  GPT-4o (2024-11-20) | 57±1 | api $4.38/M | ||
| 279 | Gemini 2.5 Flash-Lite | 57±2 | api $0.17/M | ||
| 280 |  Qwen2.5-Max (2025-01-25) | 57±1 | comparison only | ||
| 281 | Qwen2.5-Omni 7B | 57±2 | local | ||
| more from Google | |||||
| 9 | Gemini 4 Argon (limited preview) | 82±1 | limited preview | ||
| 23 | Gemini 3.8 Flash | 77±1 | api $1.50/M | ||
| 32 | Gemini 3.7 Flash | 76±1 | api $1.50/M | ||
$ what it's good at
agent tasks▁▁▃▆█▆▅▅▅▄▃▁ #190 of 300 * · 20% of its score · 2 tests
Beats o1 (2024-12-17), o3-mini, DeepSeek R1 0528 here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Mellum2 12B-A2.5B Instruct here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| BFCL V4 (December 2025 archive) | 36.9% ✎ | ▁▁▁▂██▅▅▆▂▂▂ beats 40/77 | 14% |
| Galileo Agent Leaderboard v2 (action completion) | 47.0% ✎ | ▅▃·▃▃▅▅█▃█▅▅ beats 12/19 | 5.8% |
math▁▂▃▅▆▅▄█▄▁▁▁ #226 of 398 * · 12% of its score · 1 test
Beats GPT-4o (2024-08-06), Command A (03-2025), GPT-4o (2024-11-20) here, though they rank higher overall. Trails Olmo 3 7B Instruct, DeepSeek R1 Distill Llama 8B, Phi-4-mini-reasoning 3.8B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MATH-Vision | 52.1% ✎ | ▁▁·▁··▄▁▃▇▇█ beats 4/24 | 12% |
vision & documents▁▁▃▂▁▃▄▂▆▇█▄ #99 of 147 * · 64% of its score · 2 tests
Beats DeepSeek V4 Flash Vision (Exp), GPT-4o (2024-08-06) here, though they rank higher overall. Trails Llama 4 Maverick (402B-A17B), GPT-4o (2024-05-13) here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CharXiv (reasoning questions) lab | 55.5% ✎ | ▃·▃·▃▃▃·▃▃█▅ beats 0/11 | 53% |
| MATH-Vision | 52.1% ✎ | ▁▁·▁··▄▁▃▇▇█ beats 4/24 | 12% |
other tests4 not in a task · 14% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Icelandic LLM Leaderboard average (Miðeind, Sept 2026 suite) | 26.2% ✎ | ▁▁▃▂▂▄▁▃▄▄▄█ beats 10/38 | 7.3% |
| Open PT-LLM Leaderboard average (9 Portuguese tasks) | 82.3% ✎ | ▃▁▁▁▁▁▁▁▂█▅▃ beats 269/276 | 5.3% |
| Vectara hallucination leaderboard, 2025 dataset (HHEM-2.3, factual consistency rate) | 97.1% ✎ | ▁▁▂▃▄▄█▆▃▂▂▁ beats 107/140 | 1.3% |
| Vectara hallucination leaderboard (HHEM-2.3, factual consistency rate) | 96.7% ✎ | ▁▂▁▂▅█▂▃▄▃▁▃ beats 97/98 | 0.0% |
$ where to run it
Through an API
api · $0.18/M · $0.1 in / $0.4 out per 1M tokens · 1M context · ai.google.dev ↗ · price sourceStandard base token rate from models.dev. Provider-specific tiers, long-context surcharges, caching and promotions may differ.
$ how the score was worked out · Google DeepMind Gemini model… 53%, Berkeley Function Calling Lea… 14%, Qwen/Qwen3.5-4B model card 12% and 4 more
Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works
| source | results | share of the score |
|---|---|---|
 Google DeepMind Gemini model page and model cards (lab-reported scores) · lab-reported | 1 | 53% |
 Berkeley Function Calling Leaderboard result archive | 1 | 14% |
| Qwen/Qwen3.5-4B model card | 1 | 12% |
| Miðeind Icelandic LLM Leaderboard | 1 | 7% |
| Galileo Agent Leaderboard (v1 and v2 results) | 1 | 6% |
| Open Portuguese LLM Leaderboard (archived) | 1 | 5% |
 Vectara hallucination leaderboard (vectara/hallucination-leaderboard repository) | 2 | 1% |
| prior · pull toward the middle | 1% | |
| weighted average | = 57.1 |
$ improve this page
Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.
data updated · sources and licences · json