# Meta Llama 4 Scout As of October 22, 2026, Meta Llama 4 Scout ranks #116 of 123 models overall with 24.9 ±11.6 on the LLMBenchmark Index. Llama 4 Scout ranks #98 of 108 in math, its strongest category. Meta Llama 4 Scout costs $0.175 per million input tokens and $0.50 per million output tokens. Llama 4 Scout was released on April 5, 2025. Page: https://llmbenchmark.ai/models/llama-4-scout Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: Meta Llama - Released: April 5, 2025 - Price per million input tokens: $0.175 - Price per million output tokens: $0.50 - Context window: 1.31M tokens - Overall rank: 116 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 24.9 ±11.6 (90% margin, from 4 of 7 inputs) - Artificial Analysis Intelligence Index: 6.5 Benchmark results (82 of 195): - SWE-bench Verified: 9.1% (source: SWE-bench (swebench.com), read October 22, 2026) - GPQA Diamond: 47.0% (source: GPQA (Vals AI), read October 22, 2026) - AIME: 19.0% (source: AIME (Vals AI), read October 22, 2026) - MMLU Pro: 69.6% (source: MMLU Pro (Vals AI), read October 22, 2026) - AA Intelligence Index: 6.5 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - AA Coding Index: 8.2 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - AA Agentic Index: 0.5 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - Design Arena: websites: 750 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 765 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 772 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 896 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 789 Elo (source: Design Arena, read October 22, 2026) - LiveCodeBench (Vals AI): 38.5% (source: Vals AI boards, read October 22, 2026) - MMMU Pro (Vals AI): 58.8% (source: Vals AI boards, read October 22, 2026) - MATH 500 (Vals AI): 79.2% (source: Vals AI boards, read October 22, 2026) - MGSM (Vals AI): 88.0% (source: Vals AI boards, read October 22, 2026) - SAGE (Vals AI): 34.8% (source: Vals AI boards, read October 22, 2026) - LegalBench (Vals AI): 72.0% (source: Vals AI boards, read October 22, 2026) - CorpFin (Vals AI): 46.8% (source: Vals AI boards, read October 22, 2026) - TaxEval (Vals AI): 55.2% (source: Vals AI boards, read October 22, 2026) - MortgageTax (Vals AI): 57.8% (source: Vals AI boards, read October 22, 2026) - MedQA (Vals AI): 50.9% (source: Vals AI boards, read October 22, 2026) - MedCode (Vals AI): 23.3% (source: Vals AI boards, read October 22, 2026) - MedScribe (Vals AI): 50.6% (source: Vals AI boards, read October 22, 2026) - AA Math Index: 14.0 (source: Artificial Analysis, read October 22, 2026) - GPQA Diamond (Artificial Analysis run): 58.7% (source: Artificial Analysis, read October 22, 2026) - Humanity's Last Exam (Artificial Analysis run): 3.8% (source: Artificial Analysis, read October 22, 2026) - MMLU Pro (Artificial Analysis run): 75.2% (source: Artificial Analysis, read October 22, 2026) - LiveCodeBench (Artificial Analysis run): 29.9% (source: Artificial Analysis, read October 22, 2026) - SciCode: 21.3% (source: Artificial Analysis, read October 22, 2026) - Terminal-Bench Hard (Artificial Analysis run): 1.5% (source: Artificial Analysis, read October 22, 2026) - IFBench: 39.5% (source: Artificial Analysis, read October 22, 2026) - Long context reasoning (AA-LCR): 27.7% (source: Artificial Analysis, read October 22, 2026) - τ²-Bench Telecom: 15.5% (source: Artificial Analysis, read October 22, 2026) - AIME 2025 (Artificial Analysis run): 14.0% (source: Artificial Analysis, read October 22, 2026) - GPQA Diamond (Epoch AI run): 51.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 0.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 0.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 7.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - MATH level 5: 62.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - DTBench: 57.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - LMCA: 12.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Fiction.LiveBench: 36.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Epoch Capabilities Index: 129.6 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1279 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1286 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1266 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1287 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1248 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: creative writing: 1249 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: 1118 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1304 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1252 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1255 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1273 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1206 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1207 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: French: 1283 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1278 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1263 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1265 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1280 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1265 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1235 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1293 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1286 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1286 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1278 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1275 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1285 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1257 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1269 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1242 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1143 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1106 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1117 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1125 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1148 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: humor: 1102 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: creative writing: 1126 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - Berkeley Function Calling Leaderboard (BFCL): 28.1% (source: Berkeley Function Calling Leaderboard, read October 22, 2026) - Kagi LLM Benchmark: 36.9% (source: Kagi LLM Benchmarking Project, read October 22, 2026)