ARC-Challenge
Harbor: pendingARC-Challenge — AI evaluation benchmark listed by opencompass.
Incomplete14%Knowledge & Reasoning
- Samples
- N/A
- Released
- N/A
- Scores
- 26
RTE
Recognizing Textual Entailment
The Recognizing Textual Entailment (RTE) datasets come from a series of textual entailment challenges.
How to run
ltb · rte
$ npm i -g lettokenburn-cli$ ltb bench info rte
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
21 sourced entries| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| T5-XXL 11B | 92.5 | N/A | Independent | medium | Nov 8, 2019 | arxiv.org |
| PaLM 2-M | 81.9 | N/A | Independent | medium | May 17, 2023 | arxiv.org |
| ERNIE 2.0 Large | 80.2 | N/A | Independent | medium | Jul 29, 2019 | arxiv.org |
| PaLM 540B | 79.6 | N/A | Independent | medium | Apr 5, 2022 | arxiv.org |
| PaLM 2-L | 79.3 | N/A | Independent | medium | May 17, 2023 | arxiv.org |
| PaLM 2-S | 78.7 | N/A | Independent | medium | May 17, 2023 | arxiv.org |
| PaLM 540B | 78.7 | N/A | Independent | medium | Apr 5, 2022 | arxiv.org |
| ERNIE 2.0 Base | 74.8 | N/A | Independent | medium | Jul 29, 2019 | arxiv.org |
| PaLM 540B | 72.9 | N/A | Independent | medium | Apr 5, 2022 | arxiv.org |
| GPT-3-175B | 69.0 | N/A | Independent | medium | May 28, 2020 | arxiv.org |
| ERNIE | 68.8 | N/A | Independent | medium | May 17, 2019 | arxiv.org |
| OPT 1.3B | 60.9 | N/A | Independent | medium | May 24, 2024 | arxiv.org |
| UL2 20B | 60.7 | N/A | Independent | medium | May 10, 2022 | arxiv.org |
| OPT-175B | 60.3 | N/A | Independent | medium | Dec 22, 2022 | arxiv.org |
| OPT 30B | 58.1 | N/A | Independent | medium | Dec 22, 2022 | arxiv.org |
| BLOOM 176B | 57.4 | N/A | Independent | medium | Mar 30, 2023 | arxiv.org |
| OPT-125M | 57.0 | N/A | Independent | medium | May 24, 2024 | arxiv.org |
| OPT 66B | 54.9 | N/A | Independent | medium | Mar 30, 2023 | arxiv.org |
| OPT 1.3B | 54.2 | N/A | Independent | medium | Dec 22, 2022 | arxiv.org |
| GPT-NeoX 20B | 53.8 | N/A | Independent | medium | Mar 30, 2023 | arxiv.org |
| GPT-2-XL 1.5B | 52.3 | N/A | Independent | medium | Apr 27, 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 Recognizing Textual Entailment (RTE) datasets come from a series of textual entailment challenges. Data from RTE1, RTE2, RTE3 and RTE5 is combined. Examples are constructed based on news and Wikipedia text.