LetTokenBurnMulti-Genre Natural Language Inference
The Multi-Genre Natural Language Inference (MultiNLI) dataset has 433K sentence pairs.
$ npm i -g lettokenburn-cli$ ltb bench pull multinli --n 50$ ltb bench run ./multinli -a claude-code -m anthropic/claude-opus-4-8$ ltb bench push
Runs happen on your machine with your own subscription; only the score summary is pushed. CLI docs
| Harness | Source | Confidence | Link | |||
|---|---|---|---|---|---|---|
| ERNIE 2.0 Large | 88.7 | N/A | Independent | medium | Jul 29, 2019 | arxiv.org |
| ERNIE 2.0 Base | 86.1 | N/A | Independent | medium | Jul 29, 2019 | arxiv.org |
| ERNIE | 84.0 | N/A | Independent | medium | May 17, 2019 | arxiv.org |
| GPT-2-XL 1.5B | 36.5 | 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.
The Multi-Genre Natural Language Inference (MultiNLI) dataset has 433K sentence pairs. Its size and mode of collection are modeled closely like [SNLI](/dataset/snli). MultiNLI offers ten distinct genres (Face-to-face, Telephone, 9/11, Travel, Letters, Oxford University Press, Slate, Verbatim, Goverment and Fiction) of written and spoken English data. There are matched dev/test sets which are derived from the same sources as those in the training set, and mismatched sets which do not closely resemble any seen at training time.
Source: Semantic Sentence Matching with Densely-connectedRecurrent and Co-attentive Information