whatmodel.sh / Gemini Experimental 1206
Gemini Experimental 1206
↗ share
+ contribute
Gemini Experimental 1206 is a closed-weights language model from Google, released December 2024. Licence: proprietary.
Catalogue identity notes
Comparison-only: retired or no longer listed API model, kept so its independent runs can be scored. Dated experimental Gemini API model id gemini-exp-1206 (December 6, 2024), called directly by the Aider runs below (command 'aider --model gemini/gemini-exp-1206'); experimental, no longer served. Not in the Gemini API changelog page; identity rests on the exact dated API id.
$ how it compares
The LLMs ranked either side of Gemini Experimental 1206, out of 1132 with a score, then more from Google.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 276 |  Qwen3.5 4B | 61±1 | local | ||
| 277 |  Nemotron-Cascade-14B-Thinking | 61±1 | local | ||
| 278 | Gemini Experimental 1206 | 61±2 | comparison only | ||
| 279 |  Mellum2.1 12B-A2.5B Thinking | 60±2 | local | ||
| 280 |  GPT-4.1 mini | 60±1 | api $0.70/M | ||
| 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
coding▁▁▁▃▅▇█▇▅▄▂▁ #190 of 549 * · 99% of its score · 2 tests
Beats Gemini 2.5 Pro, Qwen3-Coder-Next (80B-A3B), Grok 4.1 Fast (Reasoning) 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) | 38.2% ✎ | ▂·▂▃▅▂▃█▆▄▂▂ beats 19/49 | 67% |
| Aider code editing (133 Exercism Python exercises, two attempts) | 80.5% ✎ | ▁·▁▂▄▁▆▄█▆▂▃ beats 60/62 | 31% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · Aider polyglot benchmark runs 67%, Aider code editing benchmark… 31%
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 |
|---|---|---|
 Aider polyglot benchmark runs | 1 | 67% |
 Aider code editing benchmark runs (old edit leaderboard) | 1 | 31% |
| prior · pull toward the middle | 1% | |
| weighted average | = 60.5 |
$ 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