벤치마크 상세
AA-LCR
긴 문서 통합 추론: 긴 문서 통합 추론
공식 리더보드 보기
단순히 긴 입력을 받는 능력이 아니라 긴 자료에서 근거를 찾아 종합하는 능력을 평가합니다. v1.1 채점 변경을 적용한 공개 결과입니다.
모든 공개 결과
모델 검색 · 점수순확인 2026. 09. 07.AA-LCR v1.1 · September 2026% correct
509개 결과원문 ↗
| 순서 | 모델 / 실행 구성 | 점수 | 평가 조건·근거 |
|---|---|---|---|
| 1 | Kimi K3 (max)Kimi | 88.67 | AA-LCR v1.1 · September 2026 |
| 2 | Claude Fable 5.1 (Adaptive Reasoning, Max Effort, Default Fallback)Anthropic | 85.33 | AA-LCR v1.1 · September 2026 |
| 3 | Claude Fable 5.1 (Adaptive Reasoning, Medium Effort, Default Fallback)Anthropic | 84.67 | AA-LCR v1.1 · September 2026 |
| 4 | GPT-5.5 (xhigh)OpenAI | 84.33 | AA-LCR v1.1 · September 2026 |
| 5 | Muse Spark 1.3 (max)Meta | 84.33 | AA-LCR v1.1 · September 2026 |
| 6 | GPT-5.5 (high)OpenAI | 84.33 | AA-LCR v1.1 · September 2026 |
| 7 | Gemini 3.8 Flash (medium)Google | 84 | AA-LCR v1.1 · September 2026 |
| 8 | GPT-5.6 Sol (max)OpenAI | 84 | AA-LCR v1.1 · September 2026 |
| 9 | GPT-5.6 Luna (max)OpenAI | 83.67 | AA-LCR v1.1 · September 2026 |
| 10 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback)Anthropic | 83.67 | AA-LCR v1.1 · September 2026 |
| 11 | Muse Glimmer (high)Meta | 83.33 | AA-LCR v1.1 · September 2026 |
| 12 | GPT-5.3 Codex (xhigh)OpenAI | 83.33 | AA-LCR v1.1 · September 2026 |
| 13 | MiniMax-M3MiniMax | 83 | AA-LCR v1.1 · September 2026 |
| 14 | GPT-5.5 (medium)OpenAI | 83 | AA-LCR v1.1 · September 2026 |
| 15 | Claude Fable 5.1 (Adaptive Reasoning, Xhigh Effort, Default Fallback)Anthropic | 83 | AA-LCR v1.1 · September 2026 |
| 16 | GPT-5.6 Terra (max)OpenAI | 83 | AA-LCR v1.1 · September 2026 |
| 17 | Muse Spark 1.3 (xhigh)Meta | 83 | AA-LCR v1.1 · September 2026 |
| 18 | Gemini 3.7 Flash (medium)Google | 83 | AA-LCR v1.1 · September 2026 |
| 19 | Agnes 2.5 Pro BetaSapiens AI | 83 | AA-LCR v1.1 · September 2026 |
| 20 | GPT-5.2 (xhigh)OpenAI | 82.67 | AA-LCR v1.1 · September 2026 |
| 21 | GPT-5.2 Codex (xhigh)OpenAI | 82.33 | AA-LCR v1.1 · September 2026 |
| 22 | Claude Fable 5.1 (Adaptive Reasoning, Low Effort, Default Fallback)Anthropic | 82.33 | AA-LCR v1.1 · September 2026 |
| 23 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic | 82.33 | AA-LCR v1.1 · September 2026 |
| 24 | GPT-5.6 Sol (xhigh)OpenAI | 82.33 | AA-LCR v1.1 · September 2026 |
| 25 | Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic | 82 | AA-LCR v1.1 · September 2026 |
| 26 | GPT-5.4 (xhigh)OpenAI | 82 | AA-LCR v1.1 · September 2026 |
| 27 | Qwen3.8 27B (xhigh)Alibaba | 82 | AA-LCR v1.1 · September 2026 |
| 28 | Gemini 3.1 Pro PreviewGoogle | 82 | AA-LCR v1.1 · September 2026 |
| 29 | Claude Opus 5 (Adaptive Reasoning, Medium Effort)Anthropic | 82 | AA-LCR v1.1 · September 2026 |
| 30 | Nex-N2-ProNex AGI | 81.67 | AA-LCR v1.1 · September 2026 |
| 31 | GPT-5.6 Luna (xhigh)OpenAI | 81.67 | AA-LCR v1.1 · September 2026 |
| 32 | GPT-5.6 Sol (high)OpenAI | 81.67 | AA-LCR v1.1 · September 2026 |
| 33 | Gemini 3.7 Flash (high)Google | 81.67 | AA-LCR v1.1 · September 2026 |
| 34 | Claude Opus 5 (Adaptive Reasoning, Low Effort)Anthropic | 81.33 | AA-LCR v1.1 · September 2026 |
| 35 | DeepSeek V4 Flash Vision (Reasoning, Max Effort)DeepSeek | 81.33 | AA-LCR v1.1 · September 2026 |
| 36 | Gemini 3.8 Flash (high)Google | 81.33 | AA-LCR v1.1 · September 2026 |
| 37 | Kimi K2.6Kimi | 81 | AA-LCR v1.1 · September 2026 |
| 38 | Grok 4.6 (medium)SpaceXAI | 81 | AA-LCR v1.1 · September 2026 |
| 39 | GPT-5.5 (low)OpenAI | 81 | AA-LCR v1.1 · September 2026 |
| 40 | Grok 4.6 (xhigh)SpaceXAI | 81 | AA-LCR v1.1 · September 2026 |
| 41 | GPT-6 Astra (max)OpenAI | 80.67 | AA-LCR v1.1 · September 2026 |
| 42 | Qwen3.6 Max PreviewAlibaba | 80.67 | AA-LCR v1.1 · September 2026 |
| 43 | Grok 4.6 (low)SpaceXAI | 80.67 | AA-LCR v1.1 · September 2026 |
| 44 | Gemini 3.8 Flash (low)Google | 80.67 | AA-LCR v1.1 · September 2026 |
| 45 | Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Anthropic | 80.33 | AA-LCR v1.1 · September 2026 |
| 46 | GPT-5.6 Sol (medium)OpenAI | 80.33 | AA-LCR v1.1 · September 2026 |
| 47 | DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek | 80.33 | AA-LCR v1.1 · September 2026 |
| 48 | Qwen3.8 2.4T A95BAlibaba | 80.33 | AA-LCR v1.1 · September 2026 |
| 49 | GPT-5.6 Luna (high)OpenAI | 80.33 | AA-LCR v1.1 · September 2026 |
| 50 | Grok 4.6 (high)SpaceXAI | 80.33 | AA-LCR v1.1 · September 2026 |
| 51 | GLM-5.3-FlashZ AI | 80 | AA-LCR v1.1 · September 2026 |
| 52 | GPT-6 Astra (xhigh)OpenAI | 80 | AA-LCR v1.1 · September 2026 |
| 53 | GPT-5.1 (high)OpenAI | 80 | AA-LCR v1.1 · September 2026 |
| 54 | Gemini 3.6 Flash (high)Google | 80 | AA-LCR v1.1 · September 2026 |
| 55 | GPT-6 Astra (low)OpenAI | 80 | AA-LCR v1.1 · September 2026 |
| 56 | K2 Horizon 375B A23BMBZUAI Institute of Foundation Models | 80 | AA-LCR v1.1 · September 2026 |
| 57 | Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic | 80 | AA-LCR v1.1 · September 2026 |
| 58 | GPT-6 Astra (high)OpenAI | 80 | AA-LCR v1.1 · September 2026 |
| 59 | MiMo-V2.5-ProXiaomi | 79.67 | AA-LCR v1.1 · September 2026 |
| 60 | Qwen3.8 27B (medium)Alibaba | 79.67 | AA-LCR v1.1 · September 2026 |
| 61 | Qwen3.8-Flash-NextAlibaba | 79.67 | AA-LCR v1.1 · September 2026 |
| 62 | GLM-5.3 (max)Z AI | 79.67 | AA-LCR v1.1 · September 2026 |
| 63 | GPT-6 Astra (medium)OpenAI | 79.67 | AA-LCR v1.1 · September 2026 |
| 64 | DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek | 79.67 | AA-LCR v1.1 · September 2026 |
| 65 | Apodex 1.1Apodex | 79.33 | AA-LCR v1.1 · September 2026 |
| 66 | Kimi K3 (low)Kimi | 79.33 | AA-LCR v1.1 · September 2026 |
| 67 | Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA | 79.33 | AA-LCR v1.1 · September 2026 |
| 68 | Grok 4.5 (high)SpaceXAI | 79.33 | AA-LCR v1.1 · September 2026 |
| 69 | Kimi K2.7 CodeKimi | 79.33 | AA-LCR v1.1 · September 2026 |
| 70 | Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic | 79.33 | AA-LCR v1.1 · September 2026 |
| 71 | Muse Spark 1.2 (xhigh)Meta | 79 | AA-LCR v1.1 · September 2026 |
| 72 | Qwen3.7 MaxAlibaba | 79 | AA-LCR v1.1 · September 2026 |
| 73 | Claude Opus 5 (Adaptive Reasoning, High Effort)Anthropic | 79 | AA-LCR v1.1 · September 2026 |
| 74 | GPT-5.6 Terra (xhigh)OpenAI | 79 | AA-LCR v1.1 · September 2026 |
| 75 | Hy3Tencent | 79 | AA-LCR v1.1 · September 2026 |
| 76 | Gemini 3.7 Flash (low)Google | 78.67 | AA-LCR v1.1 · September 2026 |
| 77 | Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic | 78.67 | AA-LCR v1.1 · September 2026 |
| 78 | MiniMax-M2.7MiniMax | 78.33 | AA-LCR v1.1 · September 2026 |
| 79 | Qwen3.8 MaxAlibaba | 78.33 | AA-LCR v1.1 · September 2026 |
| 80 | Qwen3.6 PlusAlibaba | 78.33 | AA-LCR v1.1 · September 2026 |
| 81 | GLM-5.2 (max)Z AI | 78.33 | AA-LCR v1.1 · September 2026 |
| 82 | GPT-5 (high)OpenAI | 78.2 | AA-LCR v1.1 · September 2026 |
| 83 | GPT-5.6 Sol (low)OpenAI | 78 | AA-LCR v1.1 · September 2026 |
| 84 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic | 78 | AA-LCR v1.1 · September 2026 |
| 85 | Gemini 3 Flash Preview (Reasoning)Google | 78 | AA-LCR v1.1 · September 2026 |
| 86 | Kimi K2.5 (Reasoning)Kimi | 78 | AA-LCR v1.1 · September 2026 |
| 87 | Muse SparkMeta | 78 | AA-LCR v1.1 · September 2026 |
| 88 | Qwen3.5 27B (Reasoning)Alibaba | 77.67 | AA-LCR v1.1 · September 2026 |
| 89 | GPT-5.6 Terra (high)OpenAI | 77.67 | AA-LCR v1.1 · September 2026 |
| 90 | Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic | 77.67 | AA-LCR v1.1 · September 2026 |
| 91 | Muse Spark 1.1 (xhigh)Meta | 77.67 | AA-LCR v1.1 · September 2026 |
| 92 | Inkling (xhigh)Thinking Machines | 77.33 | AA-LCR v1.1 · September 2026 |
| 93 | Qwen3.5 397B A17B (Reasoning)Alibaba | 77.33 | AA-LCR v1.1 · September 2026 |
| 94 | Claude Opus 4.5 (Reasoning)Anthropic | 77.33 | AA-LCR v1.1 · September 2026 |
| 95 | Qwen3.8 27B (low)Alibaba | 77.33 | AA-LCR v1.1 · September 2026 |
| 96 | Qwen3.6 27B (Reasoning)Alibaba | 77.33 | AA-LCR v1.1 · September 2026 |
| 97 | GPT-5.4 mini (xhigh)OpenAI | 77 | AA-LCR v1.1 · September 2026 |
| 98 | GPT-5.4 (low)OpenAI | 76.67 | AA-LCR v1.1 · September 2026 |
| 99 | GPT-5.4 nano (xhigh)OpenAI | 76.67 | AA-LCR v1.1 · September 2026 |
| 100 | Qwen3.5 122B A10B (Reasoning)Alibaba | 76.33 | AA-LCR v1.1 · September 2026 |
| 101 | Quasar 438B (max, based on GLM-5.2)Multiverse Computing | 76.33 | AA-LCR v1.1 · September 2026 |
| 102 | Gemini 3.5 Flash-LiteGoogle | 76 | AA-LCR v1.1 · September 2026 |
| 103 | GPT-5 (medium)OpenAI | 76 | AA-LCR v1.1 · September 2026 |
| 104 | Motif 3Motif Technologies | 76 | AA-LCR v1.1 · September 2026 |
| 105 | Claude 4.1 Opus (Reasoning)Anthropic | 76 | AA-LCR v1.1 · September 2026 |
| 106 | Gemini 3 Pro Preview (high)Google | 76 | AA-LCR v1.1 · September 2026 |
| 107 | Claude Opus 4.7 (Non-reasoning, High Effort)Anthropic | 75.67 | AA-LCR v1.1 · September 2026 |
| 108 | GLM-5 (Reasoning)Z AI | 75.67 | AA-LCR v1.1 · September 2026 |
| 109 | Inkling SmallThinking Machines | 75.67 | AA-LCR v1.1 · September 2026 |
| 110 | Agnes 2.5 Pro AlphaSapiens AI | 75.67 | AA-LCR v1.1 · September 2026 |
| 111 | GPT-5.6 Luna (medium)OpenAI | 75 | AA-LCR v1.1 · September 2026 |
| 112 | Grok 4.3 (medium)SpaceXAI | 75 | AA-LCR v1.1 · September 2026 |
| 113 | MiMo-V2-OmniXiaomi | 75 | AA-LCR v1.1 · September 2026 |
| 114 | Grok Build 0.1 0616SpaceXAI | 74.67 | AA-LCR v1.1 · September 2026 |
| 115 | o3OpenAI | 74.67 | AA-LCR v1.1 · September 2026 |
| 116 | Motif 3 (Beta)Motif Technologies | 74.67 | AA-LCR v1.1 · September 2026 |
| 117 | DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek | 74.67 | AA-LCR v1.1 · September 2026 |
| 118 | Gemini 3.5 Flash (medium)Google | 74.33 | AA-LCR v1.1 · September 2026 |
| 119 | Gemini 3.1 Flash-LiteGoogle | 74.33 | AA-LCR v1.1 · September 2026 |
| 120 | Qwen3 Max ThinkingAlibaba | 74.33 | AA-LCR v1.1 · September 2026 |
| 121 | Claude 4.5 Haiku (Reasoning)Anthropic | 74.33 | AA-LCR v1.1 · September 2026 |
| 122 | DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek | 74.33 | AA-LCR v1.1 · September 2026 |
| 123 | Solar Pro 4Upstage | 74 | AA-LCR v1.1 · September 2026 |
| 124 | Grok 4.1 Fast (Reasoning)SpaceXAI | 74 | AA-LCR v1.1 · September 2026 |
| 125 | GPT-5.6 Terra (medium)OpenAI | 74 | AA-LCR v1.1 · September 2026 |
| 126 | Gemini 3 Pro Preview (low)Google | 74 | AA-LCR v1.1 · September 2026 |
| 127 | Grok 4.3 (low)SpaceXAI | 74 | AA-LCR v1.1 · September 2026 |
| 128 | Grok 4 Fast (Reasoning)SpaceXAI | 73.67 | AA-LCR v1.1 · September 2026 |
| 129 | GLM-5.1 (Reasoning)Z AI | 73.67 | AA-LCR v1.1 · September 2026 |
| 130 | Step 3.7 FlashStepFun | 73.67 | AA-LCR v1.1 · September 2026 |
| 131 | Gemini 3.5 Flash (high)Google | 73.33 | AA-LCR v1.1 · September 2026 |
| 132 | MiniMax-M2.5MiniMax | 73.33 | AA-LCR v1.1 · September 2026 |
| 133 | MiMo-V2-Omni-0327Xiaomi | 73.33 | AA-LCR v1.1 · September 2026 |
| 134 | DeepSeek V3.2 (Reasoning)DeepSeek | 73.33 | AA-LCR v1.1 · September 2026 |
| 135 | MiMo-V2.5Xiaomi | 73 | AA-LCR v1.1 · September 2026 |
| 136 | Grok 4.3 (high)SpaceXAI | 73 | AA-LCR v1.1 · September 2026 |
| 137 | Qwen3.7 PlusAlibaba | 73 | AA-LCR v1.1 · September 2026 |
| 138 | Ling 3.0 FlashInclusionAI | 73 | AA-LCR v1.1 · September 2026 |
| 139 | KAT Coder Pro V2KwaiKAT | 73 | AA-LCR v1.1 · September 2026 |
| 140 | GPT-5 mini (high)OpenAI | 72.33 | AA-LCR v1.1 · September 2026 |
| 141 | Claude 4.5 Sonnet (Reasoning)Anthropic | 72.33 | AA-LCR v1.1 · September 2026 |
| 142 | DeepSeek V3.2 Exp (Reasoning)DeepSeek | 72.33 | AA-LCR v1.1 · September 2026 |
| 143 | GPT-5 mini (medium)OpenAI | 72.33 | AA-LCR v1.1 · September 2026 |
| 144 | Qwen3.5 35B A3B (Reasoning)Alibaba | 72 | AA-LCR v1.1 · September 2026 |
| 145 | DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek | 72 | AA-LCR v1.1 · September 2026 |
| 146 | Kimi K2 ThinkingKimi | 72 | AA-LCR v1.1 · September 2026 |
| 147 | Qwen3 235B A22B 2507 (Reasoning)Alibaba | 72 | AA-LCR v1.1 · September 2026 |
| 148 | GLM-5-TurboZ AI | 71.67 | AA-LCR v1.1 · September 2026 |
| 149 | Doubao Seed CodeByteDance Seed | 71.67 | AA-LCR v1.1 · September 2026 |
| 150 | GPT-5 Codex (high)OpenAI | 71.67 | AA-LCR v1.1 · September 2026 |
| 151 | Solar Open2 250BUpstage | 71.67 | AA-LCR v1.1 · September 2026 |
| 152 | Qwen3.6 35B A3B (Reasoning)Alibaba | 71.67 | AA-LCR v1.1 · September 2026 |
| 153 | MiMo-V2-Flash (Feb 2026)Xiaomi | 71.33 | AA-LCR v1.1 · September 2026 |
| 154 | JT-4.1 Flash 236B A21BChina Mobile | 71.33 | AA-LCR v1.1 · September 2026 |
| 155 | GPT-5.6 Terra (low)OpenAI | 71.33 | AA-LCR v1.1 · September 2026 |
| 156 | GLM-4.7 (Reasoning)Z AI | 71 | AA-LCR v1.1 · September 2026 |
| 157 | Gemini 2.5 Flash Preview (Sep '25) (Reasoning)Google | 71 | AA-LCR v1.1 · September 2026 |
| 158 | GPT-6 Astra (Non-reasoning)OpenAI | 70.67 | AA-LCR v1.1 · September 2026 |
| 159 | Claude Opus 4.5 (Non-reasoning)Anthropic | 70.67 | AA-LCR v1.1 · September 2026 |
| 160 | MiMo-V2-Flash (Reasoning)Xiaomi | 70.67 | AA-LCR v1.1 · September 2026 |
| 161 | GLM 5V Turbo (Reasoning)Z AI | 70.33 | AA-LCR v1.1 · September 2026 |
| 162 | DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek | 70.33 | AA-LCR v1.1 · September 2026 |
| 163 | GPT-5.2 (medium)OpenAI | 70.33 | AA-LCR v1.1 · September 2026 |
| 164 | Claude 4 Sonnet (Reasoning)Anthropic | 70.33 | AA-LCR v1.1 · September 2026 |
| 165 | GPT-5.6 Luna (low)OpenAI | 70 | AA-LCR v1.1 · September 2026 |
| 166 | Qwen3.5 9B (Reasoning)Alibaba | 70 | AA-LCR v1.1 · September 2026 |
| 167 | DeepSeek V3.2 SpecialeDeepSeek | 70 | AA-LCR v1.1 · September 2026 |
| 168 | A.X-K2SK Telecom | 70 | AA-LCR v1.1 · September 2026 |
| 169 | GPT-5.5 Instant (June 2026)OpenAI | 70 | AA-LCR v1.1 · September 2026 |
| 170 | Claude Sonnet 5 (Non-reasoning, High Effort)Anthropic | 70 | AA-LCR v1.1 · September 2026 |
| 171 | Ring-2.6-1TInclusionAI | 70 | AA-LCR v1.1 · September 2026 |
| 172 | Kimi K2.6 (Non-reasoning)Kimi | 69.67 | AA-LCR v1.1 · September 2026 |
| 173 | Gemma 4 31B (Reasoning)Google | 69.67 | AA-LCR v1.1 · September 2026 |
| 174 | GPT-5.1 Codex (high)OpenAI | 69.33 | AA-LCR v1.1 · September 2026 |
| 175 | DeepSeek V3.1 Terminus (Reasoning)DeepSeek | 69.33 | AA-LCR v1.1 · September 2026 |
| 176 | Qwen3.8 27B (Non-reasoning)Alibaba | 69.33 | AA-LCR v1.1 · September 2026 |
| 177 | Mistral Medium 3.5Mistral | 69.33 | AA-LCR v1.1 · September 2026 |
| 178 | Claude Sonnet 4.6 (Non-reasoning, Low Effort)Anthropic | 69.33 | AA-LCR v1.1 · September 2026 |
| 179 | Gemini 2.5 ProGoogle | 69 | AA-LCR v1.1 · September 2026 |
| 180 | Grok 4.20 0309 v2 (Reasoning)SpaceXAI | 69 | AA-LCR v1.1 · September 2026 |
| 181 | Claude Sonnet 4.6 (Non-reasoning, High Effort)Anthropic | 68.33 | AA-LCR v1.1 · September 2026 |
| 182 | GPT-4.1OpenAI | 68.33 | AA-LCR v1.1 · September 2026 |
| 183 | MiMo-V2-ProXiaomi | 68.33 | AA-LCR v1.1 · September 2026 |
| 184 | Grok 4SpaceXAI | 68 | AA-LCR v1.1 · September 2026 |
| 185 | Grok 4.20 0309 (Reasoning)SpaceXAI | 67.67 | AA-LCR v1.1 · September 2026 |
| 186 | MiniMax-M2.1MiniMax | 67.67 | AA-LCR v1.1 · September 2026 |
| 187 | GPT-5.4 nano (medium)OpenAI | 67.33 | AA-LCR v1.1 · September 2026 |
| 188 | Kimi K2.5 (Non-reasoning)Kimi | 67.33 | AA-LCR v1.1 · September 2026 |
| 189 | GPT-5.4 mini (medium)OpenAI | 67 | AA-LCR v1.1 · September 2026 |
| 190 | Claude Opus 4.6 (Non-reasoning, High Effort)Anthropic | 67 | AA-LCR v1.1 · September 2026 |
| 191 | Qwen3.6 27B (Non-reasoning)Alibaba | 66.67 | AA-LCR v1.1 · September 2026 |
| 192 | GPT-5.1 Codex mini (high)OpenAI | 66.67 | AA-LCR v1.1 · September 2026 |
| 193 | GPT-5.5 Instant (May 2026)OpenAI | 66.33 | AA-LCR v1.1 · September 2026 |
| 194 | JT-35B-FlashChina Mobile | 65.67 | AA-LCR v1.1 · September 2026 |
| 195 | Nemotron 3 Super 120B A12B (Reasoning)NVIDIA | 65.67 | AA-LCR v1.1 · September 2026 |
| 196 | Gemma 4 26B A4B (Reasoning)Google | 65.67 | AA-LCR v1.1 · September 2026 |
| 197 | Gemini 2.5 Flash (Reasoning)Google | 65.33 | AA-LCR v1.1 · September 2026 |
| 198 | G9v3-39A5BAI9Stars | 65.33 | AA-LCR v1.1 · September 2026 |
| 199 | o1OpenAI | 65 | AA-LCR v1.1 · September 2026 |
| 200 | LongCat 2.0LongCat | 65 | AA-LCR v1.1 · September 2026 |
| 201 | GPT-5 (ChatGPT)OpenAI | 65 | AA-LCR v1.1 · September 2026 |
| 202 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Google | 64.67 | AA-LCR v1.1 · September 2026 |
| 203 | Hy3-preview (Reasoning)Tencent | 64.67 | AA-LCR v1.1 · September 2026 |
| 204 | Nova 2.0 Pro Preview (low)Amazon | 64.67 | AA-LCR v1.1 · September 2026 |
| 205 | Qwen3.5 397B A17B (Non-reasoning)Alibaba | 64.33 | AA-LCR v1.1 · September 2026 |
| 206 | Qwen3.6 35B A3B (Non-reasoning)Alibaba | 64.33 | AA-LCR v1.1 · September 2026 |
| 207 | MiniMax-M2MiniMax | 64.33 | AA-LCR v1.1 · September 2026 |
| 208 | Nova 2.0 Pro Preview (medium)Amazon | 64 | AA-LCR v1.1 · September 2026 |
| 209 | Qwen3.5 27B (Non-reasoning)Alibaba | 64 | AA-LCR v1.1 · September 2026 |
| 210 | GPT-5.5 (Non-reasoning)OpenAI | 64 | AA-LCR v1.1 · September 2026 |
| 211 | Qwen3.5 Omni PlusAlibaba | 63.67 | AA-LCR v1.1 · September 2026 |
| 212 | Qwen3 VL 235B A22B (Reasoning)Alibaba | 63.67 | AA-LCR v1.1 · September 2026 |
| 213 | Qwen3 Next 80B A3B (Reasoning)Alibaba | 63.67 | AA-LCR v1.1 · September 2026 |
| 214 | Gemma 4 12B (Reasoning)Google | 63.67 | AA-LCR v1.1 · September 2026 |
| 215 | Step 3.5 Flash 2603StepFun | 63 | AA-LCR v1.1 · September 2026 |
| 216 | Qwen3.5 4B (Reasoning)Alibaba | 63 | AA-LCR v1.1 · September 2026 |
| 217 | Qwen3.5 35B A3B (Non-reasoning)Alibaba | 63 | AA-LCR v1.1 · September 2026 |
| 218 | GPT-5.6 Sol (Non-reasoning)OpenAI | 62.33 | AA-LCR v1.1 · September 2026 |
| 219 | Qwen3 Max Thinking (Preview)Alibaba | 62 | AA-LCR v1.1 · September 2026 |
| 220 | Qwen3.5 122B A10B (Non-reasoning)Alibaba | 61.33 | AA-LCR v1.1 · September 2026 |
| 221 | Gemini 3.5 Flash (minimal)Google | 61.33 | AA-LCR v1.1 · September 2026 |
| 222 | Seed-OSS-36B-InstructByteDance Seed | 61.33 | AA-LCR v1.1 · September 2026 |
| 223 | Qwen3 30B A3B 2507 (Reasoning)Alibaba | 61.33 | AA-LCR v1.1 · September 2026 |
| 224 | K-EXAONE (Reasoning)LG AI Research | 61.33 | AA-LCR v1.1 · September 2026 |
| 225 | o4-mini (high)OpenAI | 61 | AA-LCR v1.1 · September 2026 |
| 226 | Nemotron 3.5 LightningNVIDIA | 60.33 | AA-LCR v1.1 · September 2026 |
| 227 | Nova 2.0 Lite (high)Amazon | 60.33 | AA-LCR v1.1 · September 2026 |
| 228 | Ling 3.0 TinyInclusionAI | 60.33 | AA-LCR v1.1 · September 2026 |
| 229 | K-EXAONE 2.0LG AI Research | 60 | AA-LCR v1.1 · September 2026 |
| 230 | Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)Google | 60 | AA-LCR v1.1 · September 2026 |
| 231 | Nova 2.0 Lite (medium)Amazon | 60 | AA-LCR v1.1 · September 2026 |
| 232 | Nova 2.0 Omni (medium)Amazon | 59.67 | AA-LCR v1.1 · September 2026 |
| 233 | GPT-5.6 Terra (Non-reasoning)OpenAI | 58.67 | AA-LCR v1.1 · September 2026 |
| 234 | GPT-5.4 (Non-reasoning)OpenAI | 58.33 | AA-LCR v1.1 · September 2026 |
| 235 | Grok 3SpaceXAI | 58 | AA-LCR v1.1 · September 2026 |
| 236 | DeepSeek R1 (Jan '25)DeepSeek | 57.67 | AA-LCR v1.1 · September 2026 |
| 237 | MiniMax M1 80kMiniMax | 57.67 | AA-LCR v1.1 · September 2026 |
| 238 | Nova 2.0 Omni (low)Amazon | 57.67 | AA-LCR v1.1 · September 2026 |
| 239 | K2 Think V2MBZUAI Institute of Foundation Models | 57 | AA-LCR v1.1 · September 2026 |
| 240 | DeepSeek V3.1 (Reasoning)DeepSeek | 56.67 | AA-LCR v1.1 · September 2026 |
| 241 | GPT-4o (ChatGPT)OpenAI | 56 | AA-LCR v1.1 · September 2026 |
| 242 | DeepSeek R1 0528 (May '25)DeepSeek | 55.67 | AA-LCR v1.1 · September 2026 |
| 243 | Gemini 2.5 Flash-Lite (Reasoning)Google | 55.67 | AA-LCR v1.1 · September 2026 |
| 244 | Gemini 3 Flash Preview (Non-reasoning)Google | 55.33 | AA-LCR v1.1 · September 2026 |
| 245 | Qwen3 VL 32B (Reasoning)Alibaba | 55.33 | AA-LCR v1.1 · September 2026 |
| 246 | Grok 3 mini Reasoning (high)SpaceXAI | 55.33 | AA-LCR v1.1 · September 2026 |
| 247 | EXAONE 4.5 33BLG AI Research | 54.67 | AA-LCR v1.1 · September 2026 |
| 248 | Ring-1TInclusionAI | 54.67 | AA-LCR v1.1 · September 2026 |
| 249 | Nova 2.0 Lite (low)Amazon | 54.33 | AA-LCR v1.1 · September 2026 |
| 250 | GLM-4.6 (Reasoning)Z AI | 54 | AA-LCR v1.1 · September 2026 |
| 251 | Claude 4.5 Sonnet (Non-reasoning)Anthropic | 54 | AA-LCR v1.1 · September 2026 |
| 252 | GLM-5.1 (Non-reasoning)Z AI | 53.33 | AA-LCR v1.1 · September 2026 |
| 253 | K-EXAONE (Non-reasoning)LG AI Research | 53.33 | AA-LCR v1.1 · September 2026 |
| 254 | Kimi K2Kimi | 53 | AA-LCR v1.1 · September 2026 |
| 255 | Kimi K2 0905Kimi | 53 | AA-LCR v1.1 · September 2026 |
| 256 | DeepSeek V4 Pro (Non-reasoning)DeepSeek | 53 | AA-LCR v1.1 · September 2026 |
| 257 | Magistral Medium 1.2Mistral | 53 | AA-LCR v1.1 · September 2026 |
| 258 | Grok Code Fast 1SpaceXAI | 53 | AA-LCR v1.1 · September 2026 |
| 259 | GLM-4.5 (Reasoning)Z AI | 52.67 | AA-LCR v1.1 · September 2026 |
| 260 | Qwen3 Next 80B A3B InstructAlibaba | 52.67 | AA-LCR v1.1 · September 2026 |
| 261 | Command A+Cohere | 52.67 | AA-LCR v1.1 · September 2026 |
| 262 | Qwen3.5 Omni FlashAlibaba | 52 | AA-LCR v1.1 · September 2026 |
| 263 | gpt-oss-120b (high)OpenAI | 52 | AA-LCR v1.1 · September 2026 |
| 264 | Claude 3.7 Sonnet (Non-reasoning)Anthropic | 51.67 | AA-LCR v1.1 · September 2026 |
| 265 | Qwen3 MaxAlibaba | 50 | AA-LCR v1.1 · September 2026 |
| 266 | Llama 4 MaverickMeta | 50 | AA-LCR v1.1 · September 2026 |
| 267 | Step 3.5 FlashStepFun | 50 | AA-LCR v1.1 · September 2026 |
| 268 | Gemini 2.5 Flash (Non-reasoning)Google | 49.9 | AA-LCR v1.1 · September 2026 |
| 269 | Mistral Small 4 (Reasoning)Mistral | 49.67 | AA-LCR v1.1 · September 2026 |
| 270 | Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Google | 49.67 | AA-LCR v1.1 · September 2026 |
| 271 | Claude 4.5 Haiku (Non-reasoning)Anthropic | 49.67 | AA-LCR v1.1 · September 2026 |
| 272 | GPT-4o (Nov '24)OpenAI | 49.33 | AA-LCR v1.1 · September 2026 |
| 273 | Granite 4.2 30BIBM | 49 | AA-LCR v1.1 · September 2026 |
| 274 | GLM-4.6V (Reasoning)Z AI | 48.67 | AA-LCR v1.1 · September 2026 |
| 275 | DeepSeek V3.1 (Non-reasoning)DeepSeek | 47 | AA-LCR v1.1 · September 2026 |
| 276 | Qwen3 Coder NextAlibaba | 47 | AA-LCR v1.1 · September 2026 |
| 277 | GLM-4.5-AirZ AI | 46.67 | AA-LCR v1.1 · September 2026 |
| 278 | Gemma 4 31B (Non-reasoning)Google | 46.67 | AA-LCR v1.1 · September 2026 |
| 279 | Qwen3.5 9B (Non-reasoning)Alibaba | 46 | AA-LCR v1.1 · September 2026 |
| 280 | gpt-oss-120b (low)OpenAI | 46 | AA-LCR v1.1 · September 2026 |
| 281 | Qwen3 Coder 480B A35B InstructAlibaba | 45.67 | AA-LCR v1.1 · September 2026 |
| 282 | DeepSeek V3.2 (Non-reasoning)DeepSeek | 45.67 | AA-LCR v1.1 · September 2026 |
| 283 | GPT-5.2 (Non-reasoning)OpenAI | 45.67 | AA-LCR v1.1 · September 2026 |
| 284 | DeepSeek V3.1 Terminus (Non-reasoning)DeepSeek | 45.33 | AA-LCR v1.1 · September 2026 |
| 285 | Granite 4.2 8BIBM | 45 | AA-LCR v1.1 · September 2026 |
| 286 | GPT-5.1 (Non-reasoning)OpenAI | 45 | AA-LCR v1.1 · September 2026 |
| 287 | GPT-5 nano (high)OpenAI | 45 | AA-LCR v1.1 · September 2026 |
| 288 | DeepSeek V3.2 Exp (Non-reasoning)DeepSeek | 44.67 | AA-LCR v1.1 · September 2026 |
| 289 | GPT-4.1 miniOpenAI | 44 | AA-LCR v1.1 · September 2026 |
| 290 | Claude 4 Sonnet (Non-reasoning)Anthropic | 44 | AA-LCR v1.1 · September 2026 |
| 291 | Mercury 2Inception | 43.67 | AA-LCR v1.1 · September 2026 |
| 292 | GPT-5 nano (medium)OpenAI | 43.67 | AA-LCR v1.1 · September 2026 |
| 293 | GLM-5 (Non-reasoning)Z AI | 43.67 | AA-LCR v1.1 · September 2026 |
| 294 | o3-mini (high)OpenAI | 43 | AA-LCR v1.1 · September 2026 |
| 295 | Qwen3 Max (Preview)Alibaba | 43 | AA-LCR v1.1 · September 2026 |
| 296 | GPT-5.6 Luna (Non-reasoning)OpenAI | 42.67 | AA-LCR v1.1 · September 2026 |
| 297 | Gemma 4 26B A4B (Non-reasoning)Google | 42.33 | AA-LCR v1.1 · September 2026 |
| 298 | GLM-5.2 (Non-reasoning)Z AI | 42.33 | AA-LCR v1.1 · September 2026 |
| 299 | Hy3-preview (Non-reasoning)Tencent | 42 | AA-LCR v1.1 · September 2026 |
| 300 | GLM-4.7-Flash (Reasoning)Z AI | 41.67 | AA-LCR v1.1 · September 2026 |
| 301 | Ling-2.6-1TInclusionAI | 41.67 | AA-LCR v1.1 · September 2026 |
| 302 | MiMo-V2.5-Pro (Non-reasoning)Xiaomi | 41.67 | AA-LCR v1.1 · September 2026 |
| 303 | DeepSeek V4 Flash (Non-reasoning)DeepSeek | 41.67 | AA-LCR v1.1 · September 2026 |
| 304 | G9v3-3BAI9Stars | 41.33 | AA-LCR v1.1 · September 2026 |
| 305 | Solar Open 100B (Reasoning)Upstage | 41 | AA-LCR v1.1 · September 2026 |
| 306 | NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA | 41 | AA-LCR v1.1 · September 2026 |
| 307 | GPT-4o (Aug '24)OpenAI | 41 | AA-LCR v1.1 · September 2026 |
| 308 | DeepSeek V3 0324DeepSeek | 40.67 | AA-LCR v1.1 · September 2026 |
| 309 | GLM-4.7 (Non-reasoning)Z AI | 40.67 | AA-LCR v1.1 · September 2026 |
| 310 | INTELLECT-3Prime Intellect | 39.67 | AA-LCR v1.1 · September 2026 |
| 311 | Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA | 39.67 | AA-LCR v1.1 · September 2026 |
| 312 | Nemotron Cascade 2 30B A3BNVIDIA | 39.33 | AA-LCR v1.1 · September 2026 |
| 313 | GPT-5 mini (minimal)OpenAI | 39.33 | AA-LCR v1.1 · September 2026 |
| 314 | KAT-Coder-Pro V1KwaiKAT | 38.67 | AA-LCR v1.1 · September 2026 |
| 315 | NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA | 38 | AA-LCR v1.1 · September 2026 |
| 316 | Celeris-1Celeris | 38 | AA-LCR v1.1 · September 2026 |
| 317 | Trinity Large ThinkingArcee AI | 38 | AA-LCR v1.1 · September 2026 |
| 318 | North Mini CodeCohere | 37.33 | AA-LCR v1.1 · September 2026 |
| 319 | Qwen3 4B 2507 (Reasoning)Alibaba | 37.33 | AA-LCR v1.1 · September 2026 |
| 320 | GPT-5.4 mini (Non-Reasoning)OpenAI | 37 | AA-LCR v1.1 · September 2026 |
| 321 | Ling-1TInclusionAI | 36.67 | AA-LCR v1.1 · September 2026 |
| 322 | HyperNova 60B 2605 (high, based on gpt-oss-120b)Multiverse Computing | 36.33 | AA-LCR v1.1 · September 2026 |
| 323 | MiMo-V2-Flash (Non-reasoning)Xiaomi | 36.33 | AA-LCR v1.1 · September 2026 |
| 324 | Mistral Large 3Mistral | 36 | AA-LCR v1.1 · September 2026 |
| 325 | Gemma 4 12B (Non-reasoning)Google | 35 | AA-LCR v1.1 · September 2026 |
| 326 | K2-V2 (high)MBZUAI Institute of Foundation Models | 35 | AA-LCR v1.1 · September 2026 |
| 327 | Qwen3.5 4B (Non-reasoning)Alibaba | 34.67 | AA-LCR v1.1 · September 2026 |
| 328 | gpt-oss-20b (high)OpenAI | 34.67 | AA-LCR v1.1 · September 2026 |
| 329 | Nova PremierAmazon | 34.33 | AA-LCR v1.1 · September 2026 |
| 330 | Qwen3 235B A22B 2507 InstructAlibaba | 33.9 | AA-LCR v1.1 · September 2026 |
| 331 | Qwen3 VL 8B (Reasoning)Alibaba | 33.33 | AA-LCR v1.1 · September 2026 |
| 332 | Qwen3 VL 235B A22B InstructAlibaba | 32.67 | AA-LCR v1.1 · September 2026 |
| 333 | Qwen3 Coder 30B A3B InstructAlibaba | 32.67 | AA-LCR v1.1 · September 2026 |
| 334 | Devstral 2Mistral | 32.33 | AA-LCR v1.1 · September 2026 |
| 335 | Grok 4.3 (Non-reasoning)SpaceXAI | 32.33 | AA-LCR v1.1 · September 2026 |
| 336 | Solar Pro 3Upstage | 32.33 | AA-LCR v1.1 · September 2026 |
| 337 | Gemini 2.5 Flash-Lite (Non-reasoning)Google | 32 | AA-LCR v1.1 · September 2026 |
| 338 | Devstral MediumMistral | 32 | AA-LCR v1.1 · September 2026 |
| 339 | Devstral Small (May '25)Mistral | 32 | AA-LCR v1.1 · September 2026 |
| 340 | Gemma 4 E4B (Reasoning)Google | 32 | AA-LCR v1.1 · September 2026 |
| 341 | Grok 4.1 Fast (Non-reasoning)SpaceXAI | 31.33 | AA-LCR v1.1 · September 2026 |
| 342 | Mistral Medium 3Mistral | 31.33 | AA-LCR v1.1 · September 2026 |
| 343 | Ling 2.6 FlashInclusionAI | 31.33 | AA-LCR v1.1 · September 2026 |
| 344 | Gemini 2.0 Flash (Feb '25)Google | 31.33 | AA-LCR v1.1 · September 2026 |
| 345 | gpt-oss-20b (low)OpenAI | 31 | AA-LCR v1.1 · September 2026 |
| 346 | Nova 2.0 Pro Preview (Non-reasoning)Amazon | 30 | AA-LCR v1.1 · September 2026 |
| 347 | GPT-5.4 nano (Non-Reasoning)OpenAI | 29.67 | AA-LCR v1.1 · September 2026 |
| 348 | DeepSeek V3 (Dec '24)DeepSeek | 29.33 | AA-LCR v1.1 · September 2026 |
| 349 | Mistral Small 4 (Non-reasoning)Mistral | 28.33 | AA-LCR v1.1 · September 2026 |
| 350 | LongCat Flash LiteLongCat | 28.33 | AA-LCR v1.1 · September 2026 |
| 351 | Kimi Linear 48B A3B InstructKimi | 28 | AA-LCR v1.1 · September 2026 |
| 352 | Devstral Small 2Mistral | 28 | AA-LCR v1.1 · September 2026 |
| 353 | K2-V2 (medium)MBZUAI Institute of Foundation Models | 28 | AA-LCR v1.1 · September 2026 |
| 354 | Llama 4 ScoutMeta | 27.7 | AA-LCR v1.1 · September 2026 |
| 355 | Claude 3 HaikuAnthropic | 27.67 | AA-LCR v1.1 · September 2026 |
| 356 | Claude 3.5 HaikuAnthropic | 27.33 | AA-LCR v1.1 · September 2026 |
| 357 | QwQ 32BAlibaba | 26.67 | AA-LCR v1.1 · September 2026 |
| 358 | Ministral 3 14BMistral | 26.33 | AA-LCR v1.1 · September 2026 |
| 359 | Qwen3 30B A3B 2507 InstructAlibaba | 26.33 | AA-LCR v1.1 · September 2026 |
| 360 | GLM-4.6 (Non-reasoning)Z AI | 26.33 | AA-LCR v1.1 · September 2026 |
| 361 | Ministral 3 8BMistral | 25.67 | AA-LCR v1.1 · September 2026 |
| 362 | Llama 3.1 Instruct 405BMeta | 25.33 | AA-LCR v1.1 · September 2026 |
| 363 | Grok 4.20 0309 (Non-reasoning)SpaceXAI | 25.33 | AA-LCR v1.1 · September 2026 |
| 364 | Nova 2.0 Omni (Non-reasoning)Amazon | 24.67 | AA-LCR v1.1 · September 2026 |
| 365 | Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA | 24.67 | AA-LCR v1.1 · September 2026 |
| 366 | Granite 4.2 3BIBM | 24.33 | AA-LCR v1.1 · September 2026 |
| 367 | Grok 4 Fast (Non-reasoning)SpaceXAI | 24 | AA-LCR v1.1 · September 2026 |
| 368 | NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA | 24 | AA-LCR v1.1 · September 2026 |
| 369 | Gemma 4 E4B (Non-reasoning)Google | 24 | AA-LCR v1.1 · September 2026 |
| 370 | Granite 4.1 30BIBM | 23.67 | AA-LCR v1.1 · September 2026 |
| 371 | Grok 4.20 0309 v2 (Non-reasoning)SpaceXAI | 23.33 | AA-LCR v1.1 · September 2026 |
| 372 | Cogito v2.1 (Reasoning)Deep Cogito | 22.67 | AA-LCR v1.1 · September 2026 |
| 373 | NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA | 22.67 | AA-LCR v1.1 · September 2026 |
| 374 | Mistral Small 3.1Mistral | 22.33 | AA-LCR v1.1 · September 2026 |
| 375 | Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research | 22.33 | AA-LCR v1.1 · September 2026 |
| 376 | Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research | 22 | AA-LCR v1.1 · September 2026 |
| 377 | Tri-21B-think PreviewTrillion Labs | 21.67 | AA-LCR v1.1 · September 2026 |
| 378 | NVIDIA Nemotron 3 Nano 4BNVIDIA | 21.67 | AA-LCR v1.1 · September 2026 |
| 379 | Command ACohere | 21.33 | AA-LCR v1.1 · September 2026 |
| 380 | Apriel-v1.5-15B-ThinkerServiceNow | 21.33 | AA-LCR v1.1 · September 2026 |
| 381 | Qwen3 VL 4B (Reasoning)Alibaba | 21.33 | AA-LCR v1.1 · September 2026 |
| 382 | Ring-flash-2.0InclusionAI | 21 | AA-LCR v1.1 · September 2026 |
| 383 | Nova ProAmazon | 21 | AA-LCR v1.1 · September 2026 |
| 384 | Qwen3.5 2B (Reasoning)Alibaba | 21 | AA-LCR v1.1 · September 2026 |
| 385 | NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA | 20.67 | AA-LCR v1.1 · September 2026 |
| 386 | Mistral Small 3.2Mistral | 20.33 | AA-LCR v1.1 · September 2026 |
| 387 | GLM-4.7-Flash (Non-reasoning)Z AI | 20.33 | AA-LCR v1.1 · September 2026 |
| 388 | K2-V2 (low)MBZUAI Institute of Foundation Models | 20.33 | AA-LCR v1.1 · September 2026 |
| 389 | GPT-5 nano (minimal)OpenAI | 20 | AA-LCR v1.1 · September 2026 |
| 390 | DiffusionGemma 26B A4BGoogle | 19.67 | AA-LCR v1.1 · September 2026 |
| 391 | Magistral Small 1.2Mistral | 19.33 | AA-LCR v1.1 · September 2026 |
| 392 | Jamba 1.7 LargeAI21 Labs | 19.33 | AA-LCR v1.1 · September 2026 |
| 393 | Nova LiteAmazon | 19 | AA-LCR v1.1 · September 2026 |
| 394 | Nova 2.0 Lite (Non-reasoning)Amazon | 18.67 | AA-LCR v1.1 · September 2026 |
| 395 | Devstral Small (Jul '25)Mistral | 18.67 | AA-LCR v1.1 · September 2026 |
| 396 | Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA | 18.33 | AA-LCR v1.1 · September 2026 |
| 397 | Llama 3.1 Instruct 8BMeta | 18 | AA-LCR v1.1 · September 2026 |
| 398 | Ling-flash-2.0InclusionAI | 17.67 | AA-LCR v1.1 · September 2026 |
| 399 | GLM-4.6V (Non-reasoning)Z AI | 17 | AA-LCR v1.1 · September 2026 |
| 400 | Ministral 3 3BMistral | 17 | AA-LCR v1.1 · September 2026 |
| 401 | Qwen3 VL 8B InstructAlibaba | 16.67 | AA-LCR v1.1 · September 2026 |
| 402 | Gemma 4 E2B (Non-reasoning)Google | 16.33 | AA-LCR v1.1 · September 2026 |
| 403 | Gemma 4 E2B (Reasoning)Google | 16.33 | AA-LCR v1.1 · September 2026 |
| 404 | Jamba 1.7 MiniAI21 Labs | 16 | AA-LCR v1.1 · September 2026 |
| 405 | Tri-21B-ThinkTrillion Labs | 15.67 | AA-LCR v1.1 · September 2026 |
| 406 | Llama 3.3 Instruct 70BMeta | 15.67 | AA-LCR v1.1 · September 2026 |
| 407 | Phi-4 Mini InstructMicrosoft | 15.33 | AA-LCR v1.1 · September 2026 |
| 408 | DeepSeek R1 0528 Qwen3 8BDeepSeek | 15 | AA-LCR v1.1 · September 2026 |
| 409 | Motif-2-12.7B-ReasoningMotif Technologies | 14.67 | AA-LCR v1.1 · September 2026 |
| 410 | Mi:dm K 2.5 Pro PreviewKorea Telecom | 14.67 | AA-LCR v1.1 · September 2026 |
| 411 | Qwen3.5 2B (Non-reasoning)Alibaba | 14 | AA-LCR v1.1 · September 2026 |
| 412 | Qwen3 VL 4B InstructAlibaba | 14 | AA-LCR v1.1 · September 2026 |
| 413 | HyperCLOVA X SEED Think (32B)Naver | 13.67 | AA-LCR v1.1 · September 2026 |
| 414 | Granite 4.1 8BIBM | 13.33 | AA-LCR v1.1 · September 2026 |
| 415 | Nova MicroAmazon | 13 | AA-LCR v1.1 · September 2026 |
| 416 | JT-MINIChina Mobile | 13 | AA-LCR v1.1 · September 2026 |
| 417 | Llama 3.2 Instruct 11B (Vision)Meta | 12.67 | AA-LCR v1.1 · September 2026 |
| 418 | Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIA | 12 | AA-LCR v1.1 · September 2026 |
| 419 | Granite 4.0 H SmallIBM | 11.33 | AA-LCR v1.1 · September 2026 |
| 420 | Qwen3 4B 2507 InstructAlibaba | 11.33 | AA-LCR v1.1 · September 2026 |
| 421 | Falcon-H1R-7BTII UAE | 11 | AA-LCR v1.1 · September 2026 |
| 422 | NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA | 10.67 | AA-LCR v1.1 · September 2026 |
| 423 | DeepSeek R1 Distill Qwen 14BDeepSeek | 10.33 | AA-LCR v1.1 · September 2026 |
| 424 | DeepSeek R1 Distill Llama 70BDeepSeek | 10 | AA-LCR v1.1 · September 2026 |
| 425 | Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research | 9.67 | AA-LCR v1.1 · September 2026 |
| 426 | Qwen3.5 0.8B (Reasoning)Alibaba | 9 | AA-LCR v1.1 · September 2026 |
| 427 | Mi:dm K 2.5 ProKorea Telecom | 9 | AA-LCR v1.1 · September 2026 |
| 428 | DeepSeek R1 Distill Qwen 32BDeepSeek | 8.67 | AA-LCR v1.1 · September 2026 |
| 429 | Gemma 3 12B InstructGoogle | 8.33 | AA-LCR v1.1 · September 2026 |
| 430 | Llama 3.1 Nemotron Instruct 70BNVIDIA | 8.33 | AA-LCR v1.1 · September 2026 |
| 431 | Qwen3.5 0.8B (Non-reasoning)Alibaba | 8 | AA-LCR v1.1 · September 2026 |
| 432 | Gemma 3 27B InstructGoogle | 7.33 | AA-LCR v1.1 · September 2026 |
| 433 | Granite 4.0 MicroIBM | 7 | AA-LCR v1.1 · September 2026 |
| 434 | MiniCPM-V 4.6 1.3BOpenBMB | 7 | AA-LCR v1.1 · September 2026 |
| 435 | Granite 4.0 H 1BIBM | 7 | AA-LCR v1.1 · September 2026 |
| 436 | Gemma 3 4B InstructGoogle | 6.67 | AA-LCR v1.1 · September 2026 |
| 437 | Llama 3.2 Instruct 1BMeta | 6.67 | AA-LCR v1.1 · September 2026 |
| 438 | Jamba Reasoning 3BAI21 Labs | 6.33 | AA-LCR v1.1 · September 2026 |
| 439 | MiniCPM5-1B (Reasoning)OpenBMB | 6 | AA-LCR v1.1 · September 2026 |
| 440 | Granite 4.1 3BIBM | 6 | AA-LCR v1.1 · September 2026 |
| 441 | Granite 4.0 1BIBM | 6 | AA-LCR v1.1 · September 2026 |
| 442 | LFM2.5-2.6BLiquid AI | 5.67 | AA-LCR v1.1 · September 2026 |
| 443 | MiniCPM5-1B (Non-reasoning)OpenBMB | 5 | AA-LCR v1.1 · September 2026 |
| 444 | Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research | 4.67 | AA-LCR v1.1 · September 2026 |
| 445 | Llama 3.2 Instruct 3BMeta | 4.33 | AA-LCR v1.1 · September 2026 |
| 446 | DeepSeek R1 Distill Qwen 1.5BDeepSeek | 1.67 | AA-LCR v1.1 · September 2026 |
| 447 | GLM-4.5V (Non-reasoning)Z AI | 0 | AA-LCR v1.1 · September 2026 |
| 448 | Gemma 3 270MGoogle | 0 | AA-LCR v1.1 · September 2026 |
| 449 | Qwen3 Omni 30B A3B InstructAlibaba | 0 | AA-LCR v1.1 · September 2026 |
| 450 | DeepSeek R1 Distill Llama 8BDeepSeek | 0 | AA-LCR v1.1 · September 2026 |
| 451 | Qwen3 0.6B (Non-reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 452 | LFM2 1.2BLiquid AI | 0 | AA-LCR v1.1 · September 2026 |
| 453 | Magistral Small 1Mistral | 0 | AA-LCR v1.1 · September 2026 |
| 454 | Qwen3 4B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 455 | Mistral 7B InstructMistral | 0 | AA-LCR v1.1 · September 2026 |
| 456 | Qwen3 1.7B (Non-reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 457 | GLM-4.5V (Reasoning)Z AI | 0 | AA-LCR v1.1 · September 2026 |
| 458 | Olmo 3 7B ThinkAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 459 | Sarvam M (Reasoning)Sarvam | 0 | AA-LCR v1.1 · September 2026 |
| 460 | Olmo 3.1 32B ThinkAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 461 | LFM2.5-VL-1.6BLiquid AI | 0 | AA-LCR v1.1 · September 2026 |
| 462 | Qwen3 30B A3B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 463 | Molmo2-8BAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 464 | Qwen3 235B A22B (Non-reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 465 | Solar Pro 2 (Non-reasoning)Upstage | 0 | AA-LCR v1.1 · September 2026 |
| 466 | Qwen3 14B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 467 | Sarvam 105B (high)Sarvam | 0 | AA-LCR v1.1 · September 2026 |
| 468 | LFM2.5-1.2B-InstructLiquid AI | 0 | AA-LCR v1.1 · September 2026 |
| 469 | Apertus 70B InstructSwiss AI Initiative | 0 | AA-LCR v1.1 · September 2026 |
| 470 | Qwen3 0.6B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 471 | OLMo 2 32BAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 472 | Granite 4.0 350MIBM | 0 | AA-LCR v1.1 · September 2026 |
| 473 | Qwen3 1.7B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 474 | LFM2.5-1.2B-ThinkingLiquid AI | 0 | AA-LCR v1.1 · September 2026 |
| 475 | Magistral Medium 1Mistral | 0 | AA-LCR v1.1 · September 2026 |
| 476 | LFM2 2.6BLiquid AI | 0 | AA-LCR v1.1 · September 2026 |
| 477 | Sarvam 30B (high)Sarvam | 0 | AA-LCR v1.1 · September 2026 |
| 478 | Nanbeige4.1-3BNanbeige | 0 | AA-LCR v1.1 · September 2026 |
| 479 | Tiny Aya GlobalCohere | 0 | AA-LCR v1.1 · September 2026 |
| 480 | Exaone 4.0 1.2B (Non-reasoning)LG AI Research | 0 | AA-LCR v1.1 · September 2026 |
| 481 | Llama 3 Instruct 8BMeta | 0 | AA-LCR v1.1 · September 2026 |
| 482 | Apertus 8B InstructSwiss AI Initiative | 0 | AA-LCR v1.1 · September 2026 |
| 483 | Olmo 3 7B InstructAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 484 | Olmo 3.1 32B InstructAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 485 | Qwen3 8B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 486 | Granite 4.0 H 350MIBM | 0 | AA-LCR v1.1 · September 2026 |
| 487 | Gemma 3n E4B InstructGoogle | 0 | AA-LCR v1.1 · September 2026 |
| 488 | Gemma 3n E2B InstructGoogle | 0 | AA-LCR v1.1 · September 2026 |
| 489 | Llama 3 Instruct 70BMeta | 0 | AA-LCR v1.1 · September 2026 |
| 490 | Step3 VL 10BStepFun | 0 | AA-LCR v1.1 · September 2026 |
| 491 | Molmo 7B-DAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 492 | Qwen3 32B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 493 | Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)NVIDIA | 0 | AA-LCR v1.1 · September 2026 |
| 494 | Qwen3 8B (Non-reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 495 | Qwen3 Omni 30B A3B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 496 | Qwen3 235B A22B (Reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 497 | Qwen3 32B (Non-reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 498 | Olmo 3 32B ThinkAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 499 | Gemma 3 1B InstructGoogle | 0 | AA-LCR v1.1 · September 2026 |
| 500 | Exaone 4.0 1.2B (Reasoning)LG AI Research | 0 | AA-LCR v1.1 · September 2026 |
| 501 | Reka Flash 3Reka AI | 0 | AA-LCR v1.1 · September 2026 |
| 502 | LFM2.5-8B-A1BLiquid AI | 0 | AA-LCR v1.1 · September 2026 |
| 503 | Mistral Small 3Mistral | 0 | AA-LCR v1.1 · September 2026 |
| 504 | Solar Pro 2 (Reasoning)Upstage | 0 | AA-LCR v1.1 · September 2026 |
| 505 | Qwen3 14B (Non-reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 506 | Phi-4Microsoft | 0 | AA-LCR v1.1 · September 2026 |
| 507 | Qwen3 30B A3B (Non-reasoning)Alibaba | 0 | AA-LCR v1.1 · September 2026 |
| 508 | OLMo 2 7BAllen Institute for AI | 0 | AA-LCR v1.1 · September 2026 |
| 509 | LFM2 24B A2BLiquid AI | 0 | AA-LCR v1.1 · September 2026 |
일치하는 모델이 없습니다. 검색어를 줄여 보세요.
공개된 숫자만 높은 순으로 표시합니다. 순서가 신뢰구간을 고려한 확정 순위는 아닙니다. 단순히 긴 입력을 받는 능력이 아니라 긴 자료에서 근거를 찾아 종합하는 능력을 평가합니다. v1.1 채점 변경을 적용한 공개 결과입니다.
평가 방법 확인 ↗읽는 법
전체 벤치마크단순히 긴 입력을 받는 능력이 아니라 긴 자료에서 근거를 찾아 종합하는 능력을 평가합니다. v1.1 채점 변경을 적용한 공개 결과입니다.
단순히 긴 입력을 받는 능력이 아니라 긴 자료에서 근거를 찾아 종합하는 능력을 평가합니다. v1.1 채점 변경을 적용한 공개 결과입니다.