ANLI R2
ALBERT ( using the checkpoint in this codebase ) 58.6% tops its leaderboard
Not in model cards Models label premise and hypothesis pairs from the second adversarial test round as entailment, neutral, or contradiction. The score is test accuracy.
One track of ANLI. The ANLI record keeps lab scores that combine tracks. Importers use test accuracy only and exclude development scores.
- Released
- October 2019
- Kind
- Language reasoning
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
10
Entries on its own leaderboard, 0 models we track
ALBERT ( using the checkpoint in this codebase ) tops the leaderboard with 58.6%
Best score per entry from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 58.6 ALBERT ( using the checkpoint in this codebase )
- 58.6 ynie/albert-xxlarge-v2-snli_mnli_fever_anli_R1_R2_R3-nli
- 52.1 ALUM (RoBERTa Large)
- 51.4 InfoBERT (RoBERTa Large)
- 51.4 ynie/xlnet-large-cased-snli_mnli_fever_anli_R1_R2_R3-nli
- 50.7 XLNet Large
- 49.3 ynie/roberta-large-snli_mnli_fever_anli_R1_R2_R3-nli
- 48.9 RoBERTa Large
- 48.3 BERT Large
- 34.0 GPT-3
- 1 ALBERT ( using the checkpoint in this codebase ) 58.6%
- 2 ynie/albert-xxlarge-v2-snli_mnli_fever_anli_R1_R2_R3-nli 58.6%
- 3 ALUM (RoBERTa Large) 52.1%
- 4 InfoBERT (RoBERTa Large) 51.4%
- 5 ynie/xlnet-large-cased-snli_mnli_fever_anli_R1_R2_R3-nli 51.4%
- 6 XLNet Large 50.7%
- 7 ynie/roberta-large-snli_mnli_fever_anli_R1_R2_R3-nli 49.3%
- 8 RoBERTa Large 48.9%
- 9 BERT Large 48.3%
- 10 GPT-3 34%
Source: Official ANLI R2 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | ALBERT ( using the checkpoint in this codebase ) | 58.6% | Official leaderboard | ||
| 2 | ynie/albert-xxlarge-v2-snli_mnli_fever_anli_R1_R2_R3-nli | 58.6% | Official leaderboard | ||
| 3 | ALUM (RoBERTa Large) | 52.1% | Official leaderboard | ||
| 4 | InfoBERT (RoBERTa Large) | 51.4% | Official leaderboard | ||
| 5 | ynie/xlnet-large-cased-snli_mnli_fever_anli_R1_R2_R3-nli | 51.4% | Official leaderboard | ||
| 6 | XLNet Large | 50.7% | Official leaderboard | ||
| 7 | ynie/roberta-large-snli_mnli_fever_anli_R1_R2_R3-nli | 49.3% | Official leaderboard | ||
| 8 | RoBERTa Large | 48.9% | Official leaderboard | ||
| 9 | BERT Large | 48.3% | Official leaderboard | ||
| 10 | GPT-3 | 34% | Official leaderboard |
No lab model card reports it yet
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark.
More in Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8% - SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9% - WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9% - BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4% - KMMLU-Pro In use Models answer multiple-choice questions taken from Korean National Professional Licensure exams. It tests professional knowledge used in Korean industry.
Solar Pro 4 79.2% - HLE-Verified In use Verified and revised version of Humanity's Last Exam (1,811 items) with uncertain items removed.
Seed2.0 Pro 73.6%