instruction language context benchmark
100 questions; ~100k input tokens (cl100k_base); >=128K context; 3 runs; pass@1; no tools; GPT-5.6 Luna medium judge
Updated Sep 22, 2026
Higher lcr ranks better on this benchmark.
Rank | Model | lcr | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelMA | lcr88.67% | Percentile100.00% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank02 | ModelAN | lcr85.33% | Percentile99.48% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank03 | ModelOP | lcr84.33% | Percentile98.96% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank04 | ModelOP | lcr84.00% | Percentile98.44% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank05 | ModelGO | lcr84.00% | Percentile97.92% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank06 | ModelDE | lcr84.00% | Percentile97.40% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank07 | ModelOP | lcr83.67% | Percentile96.88% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank08 | ModelME | lcr83.33% | Percentile96.35% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank09 | ModelOP | lcr83.33% | Percentile95.83% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank10 | ModelOP | lcr83.00% | Percentile95.31% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank11 | ModelMI | lcr83.00% | Percentile94.79% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank12 | ModelME | lcr83.00% | Percentile94.27% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank13 | ModelGO | lcr83.00% | Percentile93.75% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank14 | ModelOP | lcr82.33% | Percentile93.23% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank15 | ModelAN | lcr82.33% | Percentile92.71% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank16 | ModelAN | lcr82.00% | Percentile92.19% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank17 | ModelOP | lcr82.00% | Percentile91.67% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank18 | ModelAC | lcr82.00% | Percentile91.15% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank19 | ModelGO | lcr82.00% | Percentile90.63% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank20 | ModelXA | lcr81.00% | Percentile90.10% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank21 | ModelMA | lcr81.00% | Percentile89.58% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank22 | ModelOP | lcr80.67% | Percentile89.06% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank23 | ModelAC | lcr80.33% | Percentile88.54% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank24 | ModelDE | lcr80.33% | Percentile88.02% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank25 | ModelZA | lcr80.00% | Percentile87.50% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank26 | ModelOP | lcr80.00% | Percentile86.98% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank27 | ModelGO | lcr80.00% | Percentile86.46% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank28 | ModelXI | lcr79.67% | Percentile85.94% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank29 | ModelAC | lcr79.67% | Percentile85.42% | Participants193 | EvidenceB | EvaluatedN/A |
| Rank30 | ModelZA | lcr79.67% | Percentile84.90% | Participants193 | EvidenceB | EvaluatedN/A |
The leading models and scores on this benchmark.
A closer view of the leading scores on this benchmark.
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What AA LCR v1.1 measures and how its scores work.
100 questions; ~100k input tokens (cl100k_base); >=128K context; 3 runs; pass@1; no tools; GPT-5.6 Luna medium judge
Scores are shown in ratio. This benchmark is verified and has an evidence level of B.
Artificial Analysis. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
Common questions about AA LCR v1.1.
Kimi K3 is currently ranked first with 88.67%.
The current leaders are Kimi K3 (88.67%), Claude Fable 5.1 (85.33%), and GPT-5.5 (84.33%).
MiMo-V2-Omni has the lowest matched official input price at $0.14 input / $0.28 output per 1M tokens.
The fastest matched records are GPT-5 mini (348.85 tok/s via OpenAI), MiniMax M2.5 (250.50 tok/s via MiniMax), and GPT-5.1 (207.45 tok/s via OpenAI).
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.
100 questions; ~100k input tokens (cl100k_base); >=128K context; 3 runs; pass@1; no tools; GPT-5.6 Luna medium judge
Yes. Higher values rank better for this benchmark.
100 model results are currently shown.
Yes. This benchmark can contribute to the current LLMBoard capability score.
Ranking basisThis aa lcr v1.1 AI model leaderboard uses descending lcr in the benchmark original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
Selection summary
Kimi K3 currently leads AA LCR v1.1 with 88.67%. 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.