ANLI
Adversarial Natural Language Inference benchmark for challenging entailment reasoning.
9rows
scoreprimary metric
2026-05-06sampled
Metadata
Metrics
Score, Standard error (lower is better)
| Rank | Subject | Score | Model Match | Provenance | Sampled |
|---|---|---|---|---|---|
| 1 | Phi-3-small-8k-instruct | 58.10 | — | Imported | 2026-05-06 |
| 2 | gpt-3.5-turbo-1106 | 58.10 |  GPT-3.5 Turbo openai-gpt-3.5-turbo | Imported | 2026-05-06 |
| 3 | Meta-Llama-3-8B-Instruct | 57.30 |  Llama 3 8B Instruct meta-llama-llama-3-8b-instruct | Imported | 2026-05-06 |
| 4 | Phi-3-medium-128k-instruct | 55.80 | — | Imported | 2026-05-06 |
| 5 | Mixtral-8x7B-v0.1 | 55.20 | — | Imported | 2026-05-06 |
| 6 | Phi-3-mini-4k-instruct | 52.80 | — | Imported | 2026-05-06 |
| 7 | gemma-7b | 48.70 | — | Imported | 2026-05-06 |
| 8 | Mistral-7B-v0.1 | 47.10 | — | Imported | 2026-05-06 |
| 9 | Phi-4 | 42.50 |  Phi 4 microsoft-phi-4 | Imported | 2026-05-06 |
No matching rows.