reasoning benchmark
AA-LCR
Agent Arena Long Context Reasoning benchmark
Updated Aug 7, 2026
Published models15
Registry coverage15
MetricScore
EvidenceB
AA-LCR leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | TE | 73.4% | 100.0% | 15 | C | |
| 2 | MA | 71.2% | 92.9% | 15 | C | |
| 3 | MA | 70.0% | 85.7% | 15 | C | |
| 4 | AC | 68.7% | 78.6% | 15 | C | |
| 5 | AC | 68.3% | 71.4% | 15 | C | |
| 6 | AC | 66.9% | 64.3% | 15 | C | |
| 7 | AC | 66.1% | 57.1% | 15 | C | |
| 8 | NV | 65.4% | 50.0% | 15 | C | |
| 9 | AC | 63.0% | 42.9% | 15 | C | |
| 10 | MI | 62.0% | 35.7% | 15 | C | |
| 11 | AC | 58.5% | 28.6% | 15 | C | |
| 12 | NV | 58.3% | 21.4% | 15 | C | |
| 13 | AC | 57.0% | 14.3% | 15 | C | |
| 14 | AC | 25.6% | 7.1% | 15 | C | |
| 15 | AC | 4.7% | 0.0% | 15 | C |
Score distribution
Top published rows on the benchmark's original scale.
AA-LCR highlights
The top published results on this benchmark's own scale.
What is AA-LCR?
Definition and scoring fields from the benchmark registry.
Agent Arena Long Context Reasoning benchmark
Scores are shown in ratio. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- AA-LCR
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- aa-lcr|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about AA-LCR.
Which model scores highest on AA-LCR?
Hy3 is currently ranked first with 73.4%.
What does AA-LCR measure?
Agent Arena Long Context Reasoning benchmark
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
15 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is preserved as source-native evidence but is not eligible for the current overall score.