Baichuan AI·released 2023-09-201 source
Baichuan 2-7B benchmark scores: 6 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 6 benchmarks·best result 73.3 on LAMBADA (self-reported)·0 of 6 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| LAMBADA | 73.3accuracy (%) | self-reported· optimizedT1 | 2023-09-20Qwen Technical Report |
| HellaSwag | 57.33accuracy (%) | self-reported· optimizedT1 | 2023-09-20Qwen Technical Report |
| MMLU | 38.88accuracy (%) | unverified· optimizedT1 | 2023-09-20Baichuan 2: Open Large-scale Language Models |
| GSM8K | 24.6accuracy (%) | unverified· optimizedT1 | 2023-09-20Baichuan 2: Open Large-scale Language Models |
| BBH | 22.13accuracy (%) | unverified· optimizedT1 | 2023-09-20Baichuan 2: Open Large-scale Language Models |
| ARC AI2 | 10accuracy (%) | self-reported· optimizedT1 | 2023-09-20Qwen Technical Report |
Claims drawn from cited facts, not live model generation.
This model was developed by Baichuan AI and released in 2023.
2 cited facts
This model is scored on 6 benchmarks but currently holds no top score; all scores are self-reported, meaning they are vendor-claimed and not independently confirmed, so they should be treated as claims rather than verified results.
3 cited facts
This model trails the state-of-the-art leader by an average of 50.46 points, a wide gap that places it well behind the leaders, and it holds no top benchmark scores.
2 cited facts
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Baichuan 2-7B is an AI model developed by Baichuan AI, released 2023-09-20. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Baichuan 2-7B has recorded scores on 6 benchmarks, each shown with its evidence status.
Baichuan 2-7B has recorded scores on 6 benchmarks — MMLU, ARC AI2, BBH, GSM8K, HellaSwag, LAMBADA. The full table above shows each score with its evidence status.
0 of 6 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Baichuan 2-7B has 6 tracked claims: 3 self-reported, 3 unverified.