ARC-Challenge
Harbor: pendingARC-Challenge — AI evaluation benchmark listed by opencompass.
Incomplete14%Knowledge & Reasoning
- Samples
- N/A
- Released
- N/A
- Scores
- 26
CommitmentBank
The CommitmentBank is a corpus of 1,200 naturally occurring discourses whose final sentence contains a clause-embedding predicate under an entailment canceling operator (question, modal, negation, antecedent of conditional).
How to run
ltb · commitmentbank
$ npm i -g lettokenburn-cli$ ltb bench info commitmentbank
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 | |||
|---|---|---|---|---|---|---|
| PaLM 2-L | 87.5 | N/A | Independent | medium | May 17, 2023 | arxiv.org |
| PaLM 2-S | 82.1 | N/A | Independent | medium | May 17, 2023 | arxiv.org |
| PaLM 2-M | 80.4 | N/A | Independent | medium | May 17, 2023 | arxiv.org |
| GPT-3-175B | 75.6 | N/A | Independent | medium | May 28, 2020 | arxiv.org |
| BLOOM 176B | 48.2 | N/A | Independent | medium | Mar 30, 2023 | arxiv.org |
| GPT-NeoX | 48.2 | N/A | Independent | medium | Mar 30, 2023 | arxiv.org |
| OPT 66B | 44.6 | N/A | Independent | medium | Mar 30, 2023 | 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
The CommitmentBank is a corpus of 1,200 naturally occurring discourses whose final sentence contains a clause-embedding predicate under an entailment canceling operator (question, modal, negation, antecedent of conditional).