tinyqabenchmark_core-en
tinyqabenchmark_core-en — AI evaluation benchmark listed by pwc.
How to run
ltb · tinyqabenchmark-core-en
$ npm i -g lettokenburn-cli$ ltb bench info tinyqabenchmark-core-en
External harness. No Harbor adapter has been generated for this benchmark yet. `ltb bench info` prints the known links.
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
Scores
7 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| Gemma 3 4B | 86.5 | N/A | Independent | medium | May 17, 2025 | arxiv.org |
| Llama-3.2 3B | 84.6 | N/A | Independent | medium | May 17, 2025 | arxiv.org |
| Mistral 24B Instruct | 84.6 | N/A | Independent | medium | May 17, 2025 | arxiv.org |
| Ministral 8B | 80.8 | N/A | Independent | medium | May 17, 2025 | arxiv.org |
| Ministral 3B | 76.9 | N/A | Independent | medium | May 17, 2025 | arxiv.org |
| Llama-3.2 1B | 53.8 | N/A | Independent | medium | May 17, 2025 | arxiv.org |
| Mistral 7B | 50.0 | N/A | Independent | medium | May 17, 2025 | arxiv.org |
Every number links to where it was published. Low-confidence rows are muted and need per-cell verification.
Reproduced by the community
All runsLoading community runs…
About
tinyqabenchmark_core-en — AI evaluation benchmark listed by pwc.