CSQA2
Distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Full rankings
2 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 |  GPT-3.5 Turbo (older v0613) | 14.0 |
| 2 |  Llama 2-13B | 0.1 |
Frequently asked
Pulled from the CSQA2 dataset · updated daily
What does CSQA2 measure?
CSQA2 is a knowledge benchmark in the BenchGecko catalog. 2 AI models have been tested on it. Scores range from 0.1 to 14.0 out of 100.
Which model leads on CSQA2?
GPT-3.5 Turbo (older v0613) from OpenAI leads CSQA2 with a score of 14.0. The median score across 2 tested models is 7.0.
Is CSQA2 saturated?
No · the top score is 14.0 out of 100 (14%). There is still meaningful room for improvement on CSQA2.
What makes CSQA2 distinctive?
CSQA2 is a knowledge benchmark with limited overlap to the rest of the catalog · it measures capabilities that are not well-covered by other benchmarks we track.
How often is CSQA2 data refreshed?
BenchGecko pulls updates daily. New model scores on CSQA2 appear as soon as they are published by Epoch AI or the model provider.
More knowledge benchmarks
Same category · related evaluations