Baichuan 2-7B
Baichuan 2-7B.
10
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
Baichuan Sep 2023 Baichuan 2-7B
Open weights
83.8
#235 of 256
Epoch Capabilities Index
- CFLUE Knowledge 32.3% #6 /8
- T-Eval 56.5% #5 /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 | 54.2% | #53 of 85 | Claim in Baichuan 2: Open Large-scale Language Models, via Epoch AI | |
| LAMBADA | 73.3% | #18 of 26 | Claim in Qwen Technical Report, via Epoch AI | |
| BIG-Bench Hard | 41.6% | #32 of 45 | Claim in Qwen Technical Report, via Epoch AI | |
| HellaSwag | 68% | #52 of 63 | Claim in Qwen Technical Report, via Epoch AI | |
| BoolQ | 63.2% | #56 of 61 | Claim in Qwen Technical Report, via Epoch AI | |
| Chinese SimpleQA | 14% | #25 of 27 | Official leaderboard | |
| ARC-Challenge | 32.5% | #71 of 75 | Claim in Qwen Technical Report, via Epoch AI |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GSM8K | 24.6% | #56 of 70 | Claim in Qwen Technical Report, via Epoch AI |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| T-Eval | 56.5% | #5 of 12 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CFLUE Knowledge | 32.3% | #6 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)