whatmodel.sh / Gemini 2.5 Flash Preview (09-2025)
Gemini 2.5 Flash Preview (09-2025)
↗ share
+ contribute
Gemini 2.5 Flash Preview (09-2025) is a closed-weights language model from Google, released September 2025.
Catalogue identity notes
Comparison-only. Arena entry 'gemini-2.5-flash-preview-09-2025' (text, vision). Released 2025-09: Gemini API changelog: 'Launched following preview models: gemini-2.5-flash-preview-09-2025, gemini-2.5-flash-lite-preview-09-2025' (deprecations table release date September 25, 2025). Gemini API deprecations: shut down February 17, 2026.
$ how it compares
The LLMs ranked either side of Gemini 2.5 Flash Preview (09-2025), out of 828 with a score, then more from Google.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 188 |  Qwen3-Next 80B-A3B Thinking | 63±1 | api $0.41/M +local | ||
| 189 |  DeepSeek R1 (Jan '25) | 63±1 | api $4.00/M +local | ||
| 190 | Gemini 2.5 Flash Preview (09-2025) | 63±1 | comparison only | ||
| 191 | Qwen3-Next 80B-A3B Instruct | 63±1 | api $0.34/M +local | ||
| 192 |  Granite 4.2 30B | 63±1 | api $0.28/M +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▁▁▂▆█▆▅▄▄▃▂▁ #179 of 340 · 26% of its score · 3 tests
Beats o1 (2024-12-17), o3-mini, DeepSeek R1 0528 here, though they rank higher overall. Trails SmolLM3 3B, Jamba 1.5 Mini, Jamba 1.5 Large here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| τ²-bench Retail | 61.7% ✎ | █▄··▄··▄·▄·▄ beats 2/6 | 10% |
| SWE-bench Verified | 34.2% ✎ | █·█▄·······█ beats 4/6 | 8.3% |
| τ²-bench Airline | 56.7% ✎ | ▄▄······▄█▄▄ beats 2/6 | 7.5% |
coding▁▁▁▃▅▇█▇▅▄▃▁ #195 of 524 * · 51% of its score · 2 tests
Beats Qwen3-Coder-Next (80B-A3B), Qwen3-VL 235B-A22B Instruct here, though they rank higher overall. Trails QwQ-32B-Preview, Ministral 3 8B Reasoning 2512, Phi-4-reasoning 14B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Aider polyglot (225 exercises, two attempts) | 40.0% ✎ | █▄····▄··█·▄ beats 1/6 | 43% |
| SWE-bench Verified | 34.2% ✎ | █·█▄·······█ beats 4/6 | 8.3% |
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #122 of 463 * · 15% of its score · 1 test
Beats LongCat 2.0 (1.6T-A48B), GPT-5.4 nano, Step 3.5 Flash (196B-A11B) here, though they rank higher overall. Trails Gemini 2.5 Flash, Mistral Large 3 (675B-A41B), GPT-4.1 here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1403.2 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 249/379 | 15% |
vision & documents▁▁▃▃▂▃▅▄▇▇█▃ #70 of 182 * · 11% of its score · 1 test
Beats DeepSeek V4 Flash Vision (Exp), GPT-5, Inkling Small (266B-A12B) here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena vision (style controlled) | 1230.3 ✎ | ▁▁▂▂▂▂▄▅▅▆██ beats 89/145 | 11% |
other tests1 not in a task · 4.1% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Multi-IF (aggregation unspecified) | 82.5% ✎ | ▄·····▄█▄▄·▄ beats 1/6 | 4.1% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · ServiceNow-AI/Apriel-1.6-15b-… 73%, LMArena leaderboard dataset 26%
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 |
|---|---|---|
 ServiceNow-AI/Apriel-1.6-15b-Thinker model card | 5 | 73% |
 LMArena leaderboard dataset | 2 | 26% |
| prior · pull toward the middle | 1% | |
| weighted average | = 63.2 |
$ 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