reasoning benchmark
CRAG Leaderboard
CRAG (Comprehensive RAG Benchmark) is a factual question answering benchmark consisting of 4,409 question-answer pairs across 5 domains (finance, sports, music, movie, open domain) and 8 question categories. The benchmark includes mock APIs to simulate web and Knowledge Graph search, designed to represent the diverse and dynamic nature of real-world QA tasks with temporal dynamism ranging from years to seconds. It evaluates retrieval-augmented generation systems for trustworthy question answering.
Updated Aug 17, 2026
Models3
Model coverage3
MetricScore
EvidenceB
CRAG Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAM Nova ProAmazon | Score50.3% | Percentile100.0% | Participants3 | EvidenceC | Evaluated |
| Rank02 | ModelAMNova LiteAmazon | Score43.8% | Percentile50.0% | Participants3 | EvidenceC | Evaluated |
| Rank03 | ModelAMNova MicroAmazon | Score43.1% | Percentile0.0% | Participants3 | EvidenceC | Evaluated |
CRAG Highlights
The leading models and scores on this benchmark.
CRAG Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CRAG
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis crag 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.
- 01AMNova ProAmazon
- Score
- 50.3%
- Price
- $0.80 input / $3.2 output per 1M tokens
- Speed
- Up to 100 tok/s via Bedrock
Strengths
- Ranks #1 of 3 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures CRAG, not total model capability
- 02AMNova LiteAmazon
- Score
- 43.8%
- Price
- $0.06 input / $0.24 output per 1M tokens
- Speed
- Up to 100 tok/s via Bedrock
Strengths
- Ranks #2 of 3 compared models
- 50th percentile on this benchmark
- C evidence result
Considerations
- This result measures CRAG, not total model capability
- 03AMNova MicroAmazon
- Score
- 43.1%
- Price
- $0.04 input / $0.14 output per 1M tokens
- Speed
- Up to 100 tok/s via Bedrock
Strengths
- Ranks #3 of 3 compared models
- 0th percentile on this benchmark
- C evidence result
Considerations
- This result measures CRAG, not total model capability
Selection summary
Best AI Models for CRAG
Nova Pro currently leads CRAG with 50.3%. 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 CRAG?
What CRAG measures and how its scores work.
CRAG (Comprehensive RAG Benchmark) is a factual question answering benchmark consisting of 4,409 question-answer pairs across 5 domains (finance, sports, music, movie, open domain) and 8 question categories. The benchmark includes mock APIs to simulate web and Knowledge Graph search, designed to represent the diverse and dynamic nature of real-world QA tasks with temporal dynamism ranging from years to seconds. It evaluates retrieval-augmented generation systems for trustworthy question answering.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CRAG
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- crag|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CRAG.
Which model scores highest on CRAG?
Nova Pro is currently ranked first with 50.3%.
What does CRAG measure?
CRAG (Comprehensive RAG Benchmark) is a factual question answering benchmark consisting of 4,409 question-answer pairs across 5 domains (finance, sports, music, movie, open domain) and 8 question categories. The benchmark includes mock APIs to simulate web and Knowledge Graph search, designed to represent the diverse and dynamic nature of real-world QA tasks with temporal dynamism ranging from years to seconds. It evaluates retrieval-augmented generation systems for trustworthy question answering.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
3 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.