ANLI leaderboard
As of 6 Nov 2026, the top score on ANLI is 58.1%, shared by GPT 3.5 Turbo 1106 and Phi 3 Small, ahead of Llama 3-8B at 57.3%, across 11 model configurations with a published result (Epoch AI Benchmarking Hub, result dated 6 Nov 2023). Adversarially written natural-language inference. ANLI is shown for reference only and does not count toward the BenchLeader Index.
Key facts (as of 6 Nov 2026)
- GPT 3.5 Turbo 1106 and Phi 3 Small share the top ANLI score at 58.1% (Epoch AI Benchmarking Hub, 6 Nov 2026).
- ANLI: Adversarially written natural-language inference. A 2019 benchmark, saturated for current models; kept for history (Epoch AI Benchmarking Hub).
- 11 model configurations have a published ANLI result on BenchLeader (BenchLeader, 6 Nov 2026).
- ANLI does not feed the BenchLeader Index; it is shown for reference (BenchLeader methodology).
Adversarially written natural-language inference. A 2019 benchmark, saturated for current models; kept for history.
- Published by
- Epoch AI Benchmarking Hub
- Category
- Reasoning
- Index weight
- Reference only
- Models
- 11
- Data as of
- 6 Nov 2026
CC BY 4.0 — Epoch AI, ‘AI Benchmarking Hub’, epoch.ai/benchmarks. Mirrored boards credit their original publishers.
What the test looks like
Adversarially written natural-language inference.
How it is scored
Accuracy, as compiled by Epoch AI from published results.
What to keep in mind
Saturated: frontier models score near the ceiling, so it separates only older or smaller models, and results are largely self-reported by developers.
- 1GPT 3.5 Turbo 110658.1%
- 2Phi 3 Small58.1%
- 3Llama 3-8B57.3%
- 4Phi 3 (medium)55.8%
- 5Mixtral 8x7B55.2%
- 6Phi 3 Mini52.8%
- 7Gemma 7B48.7%
- 8Mistral 7B v0.347.1%
- 9Phi-242.5%
- 10Megatron-Turing NLG 530B39.7%
- 11InstructGPT 175B35.4%
| # | ||||
|---|---|---|---|---|
| 1 |  GPT 3.5 Turbo 1106 | 58.1% | 38.6 | 2023-11-06 |
| 2 |  Phi 3 Small | 58.1% | – | 2024-04-23 |
| 3 |  Llama 3-8Bopen | 57.3% | 34.9 | 2024-04-18 |
| 4 | Phi 3medium | 55.8% | 37.9 | 2024-04-23 |
| 5 |  Mixtral 8x7Bopen | 55.2% | 30.9 | 2023-12-11 |
| 6 | Phi 3 Miniopen | 52.8% | 36.9 | 2024-04-23 |
| 7 |  Gemma 7B | 48.7% | – | 2024-02-21 |
| 8 | Mistral 7B v0.3open | 47.1% | 29.0 | 2023-09-27 |
| 9 | Phi-2open ↗ | 42.5% | – | 2023-12-12 |
| 10 |  Megatron-Turing NLG 530B | 39.7% | – | 2021-10-11 |
| 11 | InstructGPT 175B | 35.4% | – | 2022-01-27 |
More reasoning benchmarks · All LLM benchmarks
Related benchmarks
Cite as: BenchLeader, “ANLI leaderboard”, data as of 6 Nov 2026, https://www.benchleader.com/benchmarks/anli.
ANLI: questions
- What does ANLI measure?
- Adversarially written natural-language inference. Scores are reported in percent of tasks solved; higher is better.
- What is the top score on ANLI?
- As of 6 Nov 2026, the highest score on ANLI is 58.1%, shared by GPT 3.5 Turbo 1106 and Phi 3 Small, ahead of Llama 3-8B at 57.3%. Scores come from Epoch AI Benchmarking Hub and are re-read daily.
- Which AI model leads ANLI?
- GPT 3.5 Turbo 1106 and Phi 3 Small tie for first on ANLI at 58.1% as of 6 Nov 2026, ahead of Llama 3-8B at 57.3%.
- How many models have ANLI results?
- 11 model configurations have a ANLI result on BenchLeader, all taken from Epoch AI Benchmarking Hub.
- Who runs ANLI and how often is it updated?
- ANLI is published by Epoch AI Benchmarking Hub. BenchLeader re-reads the published results once a day and records the date each result was published.
- Does ANLI count toward the BenchLeader Index?
- No. ANLI is shown for reference but left out of the composite index.