reasoning benchmark
AlpacaEval 2.0 Leaderboard
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 17, 2026
Models4
Model coverage4
MetricScore
EvidenceB
AlpacaEval 2.0 Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelIB | Score62.7% | Percentile100.0% | Participants4 | EvidenceC | Evaluated |
| Rank02 | ModelIB | Score62.7% | Percentile66.7% | Participants4 | EvidenceC | Evaluated |
| Rank03 | ModelDE | Score50.5% | Percentile33.3% | Participants4 | EvidenceC | Evaluated |
| Rank04 | ModelIB | Score35.2% | Percentile0.0% | Participants4 | EvidenceC | Evaluated |
AlpacaEval 2.0 Highlights
The leading models and scores on this benchmark.
AlpacaEval 2.0 Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for AlpacaEval 2.0
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis alpacaeval 2.0 AI model leaderboard uses descending score in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01IB
- Score
- 62.7%
- Speed
- Up to 50 tok/s via Replicate
Strengths
- Ranks #1 of 4 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures AlpacaEval 2.0, not total model capability
- 02
- Score
- 62.7%
- Speed
- Up to 50 tok/s via Replicate
Strengths
- Ranks #2 of 4 compared models
- 67th percentile on this benchmark
- C evidence result
Considerations
- This result measures AlpacaEval 2.0, not total model capability
- 03DEDeepSeek-V2.5DeepSeek
- Score
- 50.5%
- Speed
- Up to 100 tok/s via DeepSeek
Strengths
- Ranks #3 of 4 compared models
- 33th percentile on this benchmark
- C evidence result
Considerations
- This result measures AlpacaEval 2.0, not total model capability
- 04
- Score
- 35.2%
Strengths
- Ranks #4 of 4 compared models
- 0th percentile on this benchmark
- C evidence result
Considerations
- This result measures AlpacaEval 2.0, not total model capability
Selection summary
Best AI Models for AlpacaEval 2.0
Granite 3.3 8B Base currently leads AlpacaEval 2.0 with 62.7%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
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.