Yi-Large
Yi-Large places in the top three on AlpacaEval 2.0.
01.AI Released 13 May 2024 11
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
01.AI May 2024 Yi-Large
Closed weights
No Epoch Capabilities Index score yet
- KOR-Bench 50% #10 /33
- BigCodeBench-Hard 17.6% #66 /96
- MixEval 84.4% #7 /34
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| AlpacaEval 2.0 | 51.9% | #3 of 40 | Official leaderboard | |
| MixEval | 84.4% | #7 of 34 | Official leaderboard | |
| MMLU | 79.3% | #28 of 127 | Epoch AI | |
| Chinese SimpleQA | 51.5% | #6 of 27 | Official leaderboard | |
| WildBench | 48.9 | #12 of 47 | Official leaderboard | |
| MMLU-Pro | 58.1% | #117 of 212 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| KOR-Bench | 50% | #10 of 33 | Official leaderboard | |
| ZebraLogic | 18.9% | #21 of 46 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| BigCodeBench | 42.5% | #42 of 69 | Official leaderboard | |
| BigCodeBench-Hard | 17.6% | #66 of 96 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| HELM Lite | 47.1 | #44 of 71 | Official leaderboard |