Baichuan2-13B
Baichuan2-13B places in the top three on CFLUE Knowledge.
12
Benchmarks with a score
0
Ranked first, out of five or more models
1
In the top three
Baichuan Sep 2023 Baichuan2-13B
Open weights
92.0
#228 of 256
Epoch Capabilities Index
- CFLUE Knowledge 41.5% #3 /8
- T-Eval 50.3% #9 /12
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 | 59.2% | #44 of 85 | Claim in Nemotron-4 15B Technical Report, via Epoch AI | |
| BIG-Bench Hard | 49% | #24 of 45 | Claim in Qwen Technical Report, via Epoch AI | |
| LAMBADA | 74% | #15 of 26 | Claim in Qwen Technical Report, via Epoch AI | |
| PIQA | 78.1% | #40 of 58 | Claim in Qwen Technical Report, via Epoch AI | |
| HellaSwag | 70.8% | #47 of 63 | Claim in Qwen Technical Report, via Epoch AI | |
| CriticEval | 4.51 | #9 of 12 | Official leaderboard | |
| Chinese SimpleQA | 21.8% | #21 of 27 | Official leaderboard | |
| BoolQ | 67% | #51 of 61 | Claim in Qwen Technical Report, via Epoch AI | |
| ARC-Challenge | 38% | #64 of 75 | Claim in Qwen Technical Report, via Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 52.8% | #36 of 70 | Claim in Nemotron-4 15B Technical Report, via Epoch AI |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| T-Eval | 50.3% | #9 of 12 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CFLUE Knowledge | 41.5% | #3 of 8 | Official leaderboard |
Baichuan's models over time
Baichuan'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)