Baichuan AI·released 2023-09-061 source
Baichuan2-13B benchmark scores: 7 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 7 benchmarks·best result 74 on LAMBADA (self-reported)·0 of 7 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| LAMBADA | 74accuracy (%) | self-reported· optimizedT1 | 2023-09-06Qwen Technical Report |
| HellaSwag | 61.07accuracy (%) | self-reported· optimizedT1 | 2023-09-06Qwen Technical Report |
| PIQA | 56.2accuracy (%) | self-reported· optimizedT1 | 2023-09-06Qwen Technical Report |
| GSM8K | 52.8accuracy (%) | self-reported· optimizedT1 | 2023-09-06Nemotron-4 15B Technical Report |
| MMLU | 45.6accuracy (%) | unverified· optimizedT1 | 2023-09-06Baichuan 2: Open Large-scale Language Models |
| BBH | 32accuracy (%) | self-reported· optimizedT1 | 2023-09-06Nemotron-4 15B Technical Report |
| ARC AI2 | 17.33accuracy (%) | self-reported· optimizedT1 | 2023-09-06Qwen Technical Report |
Claims drawn from cited facts, not live model generation.
Developed by Baichuan AI, this model is a mid-size 13-billion-parameter system released in 2023. This scale balances efficiency with capability, though it requires more computational resources than compact alternatives.
4 cited facts
This model is tracked across 7 benchmarks and currently holds no top score on any of them. Because the scores are self-reported, outside evaluation has not yet confirmed them, so treat them as claims rather than verified results.
3 cited facts
Under the disclosed harness, this model trails the leader by an average of 38.44 points, a wide gap that places it well behind the front of the pack. It holds the top score on none of the benchmarks, so it shows 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
Baichuan2-13B is an AI model developed by Baichuan AI, released 2023-09-06. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Baichuan2-13B has recorded scores on 7 benchmarks, each shown with its evidence status.
Baichuan2-13B has recorded scores on 7 benchmarks — PIQA, MMLU, ARC AI2, BBH, GSM8K, HellaSwag, and 1 more. The full table above shows each score with its evidence status.
0 of 7 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Baichuan2-13B has 7 tracked claims: 6 self-reported, 1 unverified.