whatmodel.sh / Hunyuan-Standard-Vision (2024-12-31)
Hunyuan-Standard-Vision (2024-12-31)
↗ share
+ contribute
Hunyuan-Standard-Vision (2024-12-31) is a closed-weights language model from Tencent, released December 2024.
Catalogue identity notes
Comparison-only. Arena entry 'hunyuan-standard-vision-2024-12-31' (vision). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'hunyuan-standard-vision-2024-12-31' as 'Hunyuan-Standard-Vision-2024-12-31' (Tencent, Proprietary), linking https://cloud.tencent.com/document/product/1729/104753. Released 2024-12: Tencent Cloud Hunyuan version changelog (document 1729/97765) / date in the API id. Closed Tencent Cloud API model hunyuan-standard-vision, launched 2024-12-31 (the Arena name carries the launch date). Absent from the current Hunyuan overview; treated as retired.
$ how it compares
The LLMs ranked either side of Hunyuan-Standard-Vision (2024-12-31), out of 1132 with a score, then more from Tencent.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 657 |  Infinity-Instruct-3M-0625-Mistral-7B | 47±2 | local | ||
| 658 | Infinity-Instruct-3M-0613-Llama3-70B | 47±2 | local | ||
| 659 | Hunyuan-Standard-Vision (2024-12-31) | 47±4 | comparison only | ||
| 660 | Mistral7B-PairRM-SPPO-ExPO | 47±2 | local | ||
| 661 |  Stable LM 2 12B Chat | 47±6 | local | ||
| more from Tencent | |||||
| 16 |  Hy4 preview (770B-A49B) | 79±1 | api $1.25/M +local | ||
| 57 | Hunyuan Hy3 (295B-A21B) | 74±1 | api $0.23/M +local | ||
| 139 | Hy3 preview (295B-A21B) | 68±1 | local | ||
$ what it's good at
vision & documents▁▁▃▃▂▃▅▅▇▇█▃ #168 of 199 * · 93% of its score · 1 test
Beats Gemma 3 12B, Llama 3.2 90B Vision Instruct, Nova Pro here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Arena vision (style controlled) | 1041.7 ✎ | ▁▁▂▂▃▂▄▅▅▆██ beats 20/145 | 93% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 93%
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 |
|---|---|---|
 LMArena leaderboard dataset | 1 | 93% |
| prior · pull toward the middle | 7% | |
| weighted average | = 47.1 |
$ 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