HyperAI
Command Palette
Search for a command to run...
AA-LCR v1.1: Long Context Reasoning
10k에서 100k 토큰에 이르는 장문 문서에서 정보를 추출하고 추론하며 종합하는 언어 모델의 능력을 측정하는 어려운 벤치마크입니다(cl100k_base 토크나이저로 측정).
- 모델
- 259 현재, 596 전체
- 중앙값
- 61.3%
- 범위
- 0.0%–88.3%
| 순위 | 비교 | 모델 | 점수 |
|---|---|---|---|
| 201 |  Jamba 1.7 Large AI21 Labs | 19.3% | |
| 202 |  Magistral Small 1.2 Mistral | 19.3% | |
| 203 | 18.7% | ||
| 204 | Ministral 3 3B Mistral | 17.0% | |
| 205 |  Gemma 4 E2B (Reasoning) Google | 16.3% | |
| 206 | 16.3% | ||
| 207 | Jamba 1.7 Mini AI21 Labs | 16.0% | |
| 208 | 15.7% | ||
| 209 |  Tri-21B-Think Trillion Labs | 15.7% | |
| 210 |  Phi-4 Mini Instruct Microsoft | 15.3% | |
| 211 |  Motif-2-12.7B-Reasoning Motif Technologies | 14.7% | |
| 212 |  Qwen3.5 2B (Non-reasoning) Alibaba | 14.0% | |
| 213 | 13.7% | ||
| 214 |  JT-MINI China Mobile | 13.0% | |
| 215 |  Nova Micro Amazon | 13.0% | |
| 216 | 12.7% | ||
| 217 | 11.3% | ||
| 218 |  Falcon-H1R-7B TII UAE | 11.0% | |
| 219 | 10.7% | ||
| 220 |  Hermes 4 - Llama-3.1 70B (Reasoning) Nous Research | 9.7% | |
| 221 |  Mi:dm K 2.5 Pro Korea Telecom | 9.0% | |
| 222 | Qwen3.5 0.8B (Reasoning) Alibaba | 9.0% | |
| 223 | Qwen3.5 0.8B (Non-reasoning) Alibaba | 8.0% | |
| 224 | 7.0% | ||
| 225 | 7.0% | ||
| 226 |  MiniCPM-V 4.6 1.3B OpenBMB | 7.0% | |
| 227 | Jamba Reasoning 3B AI21 Labs | 6.3% | |
| 228 |  K2 Horizon 0.9B Institute of Foundation Models | 6.3% | |
| 229 | MiniCPM5-1B (Reasoning) OpenBMB | 6.0% | |
| 230 |  LFM2.5-2.6B Liquid AI | 5.7% | |
| 231 | MiniCPM5-1B (Non-reasoning) OpenBMB | 5.0% | |
| 232 | Hermes 4 - Llama-3.1 70B (Non-reasoning) Nous Research | 4.7% | |
| 233 |  Apertus 70B Instruct Swiss AI Initiative | 0.0% | |
| 234 | Apertus 8B Instruct Swiss AI Initiative | 0.0% | |
| 235 |  Exaone 4.0 1.2B (Non-reasoning) LG AI Research | 0.0% | |
| 236 | Exaone 4.0 1.2B (Reasoning) LG AI Research | 0.0% | |
| 237 | Gemma 3 270M Google | 0.0% | |
| 238 | 0.0% | ||
| 239 | 0.0% | ||
| 240 | LFM2 24B A2B Liquid AI | 0.0% | |
| 241 | LFM2.5-1.2B-Instruct Liquid AI | 0.0% | |
| 242 | LFM2.5-1.2B-Thinking Liquid AI | 0.0% | |
| 243 | LFM2.5-8B-A1B Liquid AI | 0.0% | |
| 244 | LFM2.5-VL-1.6B Liquid AI | 0.0% | |
| 245 |  Molmo 7B-D Allen Institute for AI | 0.0% | |
| 246 | Molmo2-8B Allen Institute for AI | 0.0% | |
| 247 |  Nanbeige4.1-3B Nanbeige | 0.0% | |
| 248 | Olmo 3.1 32B Instruct Allen Institute for AI | 0.0% | |
| 249 | Olmo 3.1 32B Think Allen Institute for AI | 0.0% | |
| 250 | Olmo 3 7B Instruct Allen Institute for AI | 0.0% |
