Yi 6B
Yi 6B.
11
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
01.AI Nov 2023 Yi 6B
Open weights
94.4
#225 of 256
Epoch Capabilities Index
- MedQA 49.7% #62 /71
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 | |
|---|---|---|---|---|
| MMLU | 63.2% | #38 of 85 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI | |
| BIG-Bench Hard | 47.2% | #26 of 45 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI | |
| WinoGrande | 71.3% | #44 of 76 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI | |
| MuSR | 39.4% | #61 of 98 | Official leaderboard | |
| ARC-Challenge | 50.3% | #47 of 75 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI | |
| HellaSwag | 74.4% | #40 of 63 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI | |
| MMLU-Pro | 26.5% | #186 of 212 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 44.9% | #41 of 70 | Claim in Yi: Open Foundation Models by 01.AI, via Epoch AI |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MedQA | 49.7% | #62 of 71 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Open LLM Leaderboard v2 | 13.6 | #79 of 99 | Official leaderboard | |
| HELM Lite | 25.4 | #65 of 71 | Official leaderboard |
01.AI's models over time
01.AI's models in color, against every other model on the Epoch Capabilities Index, by release date.
Source: Epoch Capabilities Index, Epoch AI (CC BY 4.0)