whatmodel.sh / Hunyuan-Large (2025-02-10)
Hunyuan-Large (2025-02-10)
↗ share
+ contribute
Hunyuan-Large (2025-02-10) is a closed-weights language model from Tencent, released February 2025.
Catalogue identity notes
Comparison-only. Arena entry 'hunyuan-large-2025-02-10' (text). LMArena's leaderboard table (arena-leaderboard space @6f2eeeb) labels 'hunyuan-large-2025-02-10' as 'Hunyuan-Large-2025-02-10' (Tencent, Proprietary), linking https://cloud.tencent.com/document/product/1729/104753. Released 2025-02: Tencent Cloud Hunyuan version changelog (document 1729/97765) / date in the API id. The 2025-02-10 version update of Tencent Cloud's hunyuan-large API model (Tencent changelog dates the version; no dated API id). The open Tencent-Hunyuan-Large weights (2024-11) were not updated, so this is treated as closed. Retired.
$ how it compares
The LLMs ranked either side of Hunyuan-Large (2025-02-10), out of 1132 with a score, then more from Tencent.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 368 |  Qwen2.5 Coder 32B Instruct | 57±1 | api $0.74/M +local | ||
| 369 | Qwen3 4B Thinking 2507 | 57±1 | local | ||
| 370 | Hunyuan-Large (2025-02-10) | 57±3 | comparison only | ||
| 371 |  Step 1o Vision 32K High Resolution | 56±4 | comparison only | ||
| 372 |  Gemini 1.5 Pro Experimental (0827) | 56±1 | comparison only | ||
| 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
chat & writing▁▁▁▃▅▅▆█▆▆▆▂ #251 of 579 * · 95% of its score · 1 test
Beats Seed-OSS 36B Instruct, Nemotron-Cascade-14B-Thinking, Granite 4.2 8B here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, LFM2.5 1.2B Thinking, Gemma 3 12B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LMArena (text) | 1326.3 ✎ | ▁▁▁▂▃▃▃▆▆▇█▃ beats 163/379 | 95% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · LMArena leaderboard dataset 95%
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 | 95% |
| prior · pull toward the middle | 5% | |
| weighted average | = 56.6 |
$ 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