reasoning benchmark
FRAMES Leaderboard
FRAMES is a unified evaluation dataset of 824 challenging multi-hop questions for testing retrieval-augmented generation systems.
Updated Sep 5, 2026
Models2
Model coverage2
MetricScore
EvidenceB
FRAMES Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | Score87.00% | Percentile100.00% | Participants2 | EvidenceC | Evaluated |
| Rank02 | ModelDE | Score73.30% | Percentile0.00% | Participants2 | EvidenceC | Evaluated |
FRAMES Highlights
The leading models and scores on this benchmark.
FRAMES Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for FRAMES
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is FRAMES?
What FRAMES measures and how its scores work.
FRAMES is a benchmark in the reasoning category that uses questions requiring integration of 2-15 Wikipedia articles per question.
It measures factuality, retrieval accuracy, and reasoning capabilities, reported as Score in ratio units.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- FRAMES
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about FRAMES.
Which model scores highest on FRAMES?
Kimi K2-Thinking-0905 is currently ranked first with 87.00%.
What are the top three models on FRAMES?
The current leaders are Kimi K2-Thinking-0905 (87.00%) and DeepSeek-V3 (73.30%).
Which FRAMES model has the lowest official input price?
No matched official input price is currently available.
Which models are fastest among FRAMES results?
The fastest matched records are DeepSeek-V3 (100.00 tok/s via DeepSeek).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.