reasoning benchmark
AlpacaEval 2.0
AlpacaEval 2.0 is a length-controlled automatic evaluator for instruction-following language models that uses GPT-4 Turbo to assess model responses against a baseline. It evaluates models on 805 diverse instruction-following tasks including creative writing, classification, programming, and general knowledge questions. The benchmark achieves 0.98 Spearman correlation with ChatBot Arena while being fast (< 3 minutes) and affordable (< $10 in OpenAI credits). It addresses length bias in automatic evaluation through length-controlled win-rates and uses weighted scoring based on response quality.
Updated Aug 11, 2026
Models4
Model coverage4
MetricScore
EvidenceB
AlpacaEval 2.0 Ranking
Higher score ranks better on this benchmark.
| 01 | IB | 62.7% | 100.0% | 4 | C | |
| 02 | IB | 62.7% | 66.7% | 4 | C | |
| 03 | DE | 50.5% | 33.3% | 4 | C | |
| 04 | IB | 35.2% | 0.0% | 4 | C |
AlpacaEval 2.0 Score Distribution
A closer view of the leading scores on this benchmark.
AlpacaEval 2.0 Highlights
The leading models and scores on this benchmark.
What is AlpacaEval 2.0?
What AlpacaEval 2.0 measures and how its scores work.
AlpacaEval 2.0 is a length-controlled automatic evaluator for instruction-following language models that uses GPT-4 Turbo to assess model responses against a baseline. It evaluates models on 805 diverse instruction-following tasks including creative writing, classification, programming, and general knowledge questions. The benchmark achieves 0.98 Spearman correlation with ChatBot Arena while being fast (< 3 minutes) and affordable (< $10 in OpenAI credits). It addresses length bias in automatic evaluation through length-controlled win-rates and uses weighted scoring based on response quality.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- AlpacaEval 2.0
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- alpacaeval-2.0|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about AlpacaEval 2.0.
Which model scores highest on AlpacaEval 2.0?
Granite 3.3 8B Base is currently ranked first with 62.7%.
What does AlpacaEval 2.0 measure?
AlpacaEval 2.0 is a length-controlled automatic evaluator for instruction-following language models that uses GPT-4 Turbo to assess model responses against a baseline. It evaluates models on 805 diverse instruction-following tasks including creative writing, classification, programming, and general knowledge questions. The benchmark achieves 0.98 Spearman correlation with ChatBot Arena while being fast (< 3 minutes) and affordable (< $10 in OpenAI credits). It addresses length bias in automatic evaluation through length-controlled win-rates and uses weighted scoring based on response quality.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
4 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.