long context benchmark
AA-LCR Leaderboard
Agent Arena Long Context Reasoning benchmark
Updated Aug 17, 2026
Models18
Model coverage18
MetricScore
EvidenceB
AA-LCR Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelME | Score80.0% | Percentile100.0% | Participants18 | EvidenceC | Evaluated |
| Rank02 | ModelTE | Score73.4% | Percentile94.1% | Participants18 | EvidenceC | Evaluated |
| Rank03 | ModelMA | Score71.2% | Percentile88.2% | Participants18 | EvidenceC | Evaluated |
| Rank04 | ModelUP | Score71.0% | Percentile82.3% | Participants18 | EvidenceC | Evaluated |
| Rank05 | ModelMA | Score70.0% | Percentile76.5% | Participants18 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Score68.7% | Percentile70.6% | Participants18 | EvidenceC | Evaluated |
| Rank07 | ModelAC | Score68.3% | Percentile64.7% | Participants18 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Score66.9% | Percentile58.8% | Participants18 | EvidenceC | Evaluated |
| Rank09 | ModelAC | Score66.1% | Percentile52.9% | Participants18 | EvidenceC | Evaluated |
| Rank10 | ModelNV | Score65.4% | Percentile47.1% | Participants18 | EvidenceC | Evaluated |
| Rank11 | ModelAC | Score63.0% | Percentile41.2% | Participants18 | EvidenceC | Evaluated |
| Rank12 | ModelMI | Score62.0% | Percentile35.3% | Participants18 | EvidenceC | Evaluated |
| Rank13 | ModelAC | Score58.5% | Percentile29.4% | Participants18 | EvidenceC | Evaluated |
| Rank14 | ModelNV | Score58.3% | Percentile23.5% | Participants18 | EvidenceC | Evaluated |
| Rank15 | ModelAC | Score57.0% | Percentile17.6% | Participants18 | EvidenceC | Evaluated |
| Rank16 | ModelNV | Score52.0% | Percentile11.8% | Participants18 | EvidenceC | Evaluated |
| Rank17 | ModelAC | Score25.6% | Percentile5.9% | Participants18 | EvidenceC | Evaluated |
| Rank18 | ModelAC | Score4.7% | Percentile0.0% | Participants18 | EvidenceC | Evaluated |
AA-LCR Highlights
The leading models and scores on this benchmark.
AA-LCR Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for AA-LCR
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis aa-lcr 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.
- 01MEMuse Glimmer-30BMeta
- Score
- 80.0%
Strengths
- Ranks #1 of 18 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures AA-LCR, not total model capability
- 02TEHy3Tencent
- Score
- 73.4%
Strengths
- Ranks #2 of 18 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures AA-LCR, not total model capability
- 03MAMistral Small 4Mistral AI
- Score
- 71.2%
- Price
- $0.15 input / $0.60 output per 1M tokens
- Speed
- Up to 4.3 tok/s via Mistral AI
Strengths
- Ranks #3 of 18 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures AA-LCR, not total model capability
- 04UPSolar Pro 4Upstage
- Score
- 71.0%
- Price
- $0.30 input / $1.2 output per 1M tokens
Strengths
- Ranks #4 of 18 compared models
- 82th percentile on this benchmark
- C evidence result
Considerations
- This result measures AA-LCR, not total model capability
- 05MAKimi K2.5Moonshot AI
- Score
- 70.0%
- Price
- $0.60 input / $3.0 output per 1M tokens
Strengths
- Ranks #5 of 18 compared models
- 76th percentile on this benchmark
- C evidence result
Considerations
- This result measures AA-LCR, not total model capability
Selection summary
Best AI Models for AA-LCR
Muse Glimmer-30B currently leads AA-LCR with 80.0%. 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 AA-LCR?
What AA-LCR measures and how its scores work.
Agent Arena Long Context Reasoning benchmark
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- AA-LCR
- Modality
- text
- Primary category
- long context
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- aa-lcr|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about AA-LCR.
Which model scores highest on AA-LCR?
Muse Glimmer-30B is currently ranked first with 80.0%.
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?
18 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.