Baichuan2-13B
Baichuan2-13B.
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Baichuan2-13B
Open weights
103.1
#242 of 271
Epoch Capabilities Index
- LAMBADA 74% #15 /26
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 | |
|---|---|---|---|---|
| BIG-Bench Hard | 49% | #24 of 45 | Epoch AI | |
| LAMBADA | 74% | #15 of 26 | Epoch AI | |
| MMLU | 59.2% | #84 of 127 | Epoch AI | |
| PIQA | 78.1% | #40 of 58 | Epoch AI | |
| HellaSwag | 70.8% | #52 of 74 | Epoch AI | |
| CriticEval | 4.51 | #6 of 8 | Official leaderboard | |
| Chinese SimpleQA | 21.8% | #21 of 27 | Official leaderboard | |
| BoolQ | 67% | #59 of 75 | Epoch AI | |
| ARC-Challenge | 38% | #64 of 75 | Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 52.8% | #37 of 82 | Epoch AI |
Baichuan's models over time
Baichuan's models in color, against every other model on the Epoch Capabilities Index, by release date.