Baichuan AI·released 2023-06-011 source
Baichuan1-7B benchmark scores: 4 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 4 benchmarks·best result 52.4 on PIQA (self-reported)·0 of 4 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| PIQA | 52.4accuracy (%) | self-reported· optimizedT1 | 2023-06-01Qwen Technical Report |
| MMLU | 23.07accuracy (%) | unverified· optimizedT1 | 2023-06-01Baichuan 2: Open Large-scale Language Models |
| BBH | 9.97accuracy (%) | unverified· optimizedT1 | 2023-06-01Baichuan 2: Open Large-scale Language Models |
| GSM8K | 9.2accuracy (%) | unverified· optimizedT1 | 2023-06-01Baichuan 2: Open Large-scale Language Models |
Claims drawn from cited facts, not live model generation.
Developed by Baichuan AI, this model is a 7-billion-parameter system released in 2023. That compact scale implies efficiency and lower cost at the small end, with less headroom than larger frontier-scale models.
4 cited facts
This model is currently scored on four tracked benchmarks. It holds no current top score on any of them. These results are self-reported, meaning outside evaluation has not independently confirmed them; treat them as claims rather than verified results.
3 cited facts
With an average gap of 61.55 points to the top score, this model sits well behind the leaders on its benchmarks, a wide gap rather than a front-of-pack result. It claims the top score on none of the tracked benchmarks (0), so it has no category leadership yet.
2 cited facts
2 facts cross-checked across data sources: 2 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: curated_param_counts, epoch_benchmarks
Baichuan1-7B is an AI model developed by Baichuan AI, released 2023-06-01. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Baichuan1-7B has recorded scores on 4 benchmarks, each shown with its evidence status.
Baichuan1-7B has recorded scores on 4 benchmarks — PIQA, MMLU, BBH, GSM8K. The full table above shows each score with its evidence status.
0 of 4 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Baichuan1-7B has 4 tracked claims: 1 self-reported, 3 unverified.