whatmodel.sh / Yi-Large Preview
Yi-Large Preview
↗ share
+ contribute
Yi-Large Preview is a closed-weights language model from 01.AI, released May 2024. Licence: proprietary.
Catalogue identity notes
Comparison-only. 01.AI's pre-release API model 'yi-large-preview' (AlpacaEval config 'Yi-Large Preview', added 2024-05-08 in PR #304, served from 01.AI's endpoint). LMArena's leaderboard table (arena-leaderboard Space @6f2eeeb) lists key 'yi-large-preview' as 'Yi-Large-preview' (01 AI, Proprietary) linking https://platform.lingyiwanwu.com/docs. Kept separate from 'yi-large' (each source labels them as two models with different scores). Results: ZeroEval, WildBench v2, AlpacaEval 2.0.
$ how it compares
The LLMs ranked either side of Yi-Large Preview, out of 828 with a score, then more from 01.AI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 371 |  Bielik 11B v2.1 Instruct | 53±3 | local | ||
| 372 |  Llama 3.1 70B Instruct | 52±1 | api $0.72/M +local | ||
| 373 | Yi-Large Preview | 52±1 | comparison only | ||
| 374 |  Qwen2.5-Math 7B Instruct | 52±2 | local | ||
| 375 |  LFM2.5 8B-A1B | 52±1 | local | ||
| more from 01.AI | |||||
| 308 | Yi-Lightning | 55±1 | api price unknown | ||
| 396 | Yi-Large | 51±1 | comparison only | ||
| 414 | Yi 34B 200K (base) | 50±5 | local | ||
$ what it's good at
coding▁▁▁▃▅▇█▇▅▄▃▁ #303 of 524 * · 17% of its score · 1 test
Beats Qwen3-VL 32B Instruct, Solar Open 100B (102B-A12B), GLM-4.7-Flash here, though they rank higher overall. Trails DeepSeek LLM 67B Chat, QwQ-32B-Preview, InternLM2.5 20B Chat here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| CRUXEval (ZeroEval, 800 problems) | 60.4% ✎ | ▁▂▆▃▆█▆▃▂·▁▁ beats 21/47 | 17% |
chat & writing▁▁▁▃▅▄▆█▇▇▇▃ #241 of 463 * · 30% of its score · 1 test
Beats Granite 4.2 8B, Qwen3-VL 30B-A3B Thinking, Mistral Small 4 (119B-A6.5B) here, though they rank higher overall. Trails LFM2.5 1.2B Instruct, Granite 4.0 H Micro 3B, Gemma 3n E4B here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| AlpacaEval 2 length-controlled | 51.9% ✎ | ▁▂▂▃▆▆█▆▄▄▁▁ beats 109/122 | 30% |
math▁▂▃▅▇▅▅█▄▁▁▁ #388 of 462 * · 6.1% of its score · 1 test
Trails Qwen3 0.6B, Gemma 7B (base), LFM2 700M here, though they rank lower overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| GSM8K (ZeroEval, zero-shot) | 82.6% ✎ | ▁▄·▁▄█▅▅▅███ beats 14/43 | 6.1% |
other tests3 not in a task · 47% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| MMLU-Redux (ZeroEval, 2,778 questions) | 82.2% ✎ | ▁·▁▁▄▄▄▅█▄▂▁ beats 36/53 | 27% |
| ZebraLogic (ZeroEval, 1,000 puzzles) | 18.9% ✎ | ▁▁▃▆██▁▁·▁▁▁ beats 27/57 | 12% |
| WildBench v2 WB-Score (task macro) | 55.2946 WB-Score ✎ | ▁·▁▁·▃█▄▇▆▅▆ beats 48/52 | 7.6% |
$ where to run it
No verified API or download recorded yet · add one
$ how the score was worked out · WildEval ZeroEval published r… 62%, AlpacaEval 1.0 and 2.0 leader… 30%, WildBench v2 leaderboard data… 8%
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 |
|---|---|---|
 WildEval ZeroEval published results | 4 | 62% |
 AlpacaEval 1.0 and 2.0 leaderboards (tatsu-lab/alpaca_eval repository) | 1 | 30% |
| WildBench v2 leaderboard data (Ai2) | 1 | 8% |
| prior · pull toward the middle | 0% | |
| weighted average | = 52.4 |
$ 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