# OpenAI GPT-5 Nano As of October 22, 2026, OpenAI GPT-5 Nano ranks #105 of 123 models overall with 35.6 ±10.3 on the LLMBenchmark Index. GPT-5 Nano ranks #97 of 122 in reasoning, its strongest category. OpenAI GPT-5 Nano costs $0.05 per million input tokens and $0.40 per million output tokens. GPT-5 Nano was released on August 7, 2025. Page: https://llmbenchmark.ai/models/gpt-5-nano Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: OpenAI - Released: August 7, 2025 - Price per million input tokens: $0.05 - Price per million output tokens: $0.40 - Context window: 400K tokens - Overall rank: 105 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 35.6 ±10.3 (90% margin, from 5 of 7 inputs) - Artificial Analysis Intelligence Index: 13.0 Benchmark results (87 of 195): - SWE-bench Verified: 34.8% (source: SWE-bench (swebench.com), read October 22, 2026) - GPQA Diamond: 63.4% (source: GPQA (Vals AI), read October 22, 2026) - AIME: 81.2% (source: AIME (Vals AI), read October 22, 2026) - MMLU Pro: 76.1% (source: MMLU Pro (Vals AI), read October 22, 2026) - AA Intelligence Index: 13.0 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - Design Arena: websites: 1101 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 1064 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 1044 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 1056 Elo (source: Design Arena, read October 22, 2026) - Design Arena: 3D: 965 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 1084 Elo (source: Design Arena, read October 22, 2026) - LiveCodeBench (Vals AI): 70.2% (source: Vals AI boards, read October 22, 2026) - MMMU Pro (Vals AI): 70.9% (source: Vals AI boards, read October 22, 2026) - MATH 500 (Vals AI): 93.8% (source: Vals AI boards, read October 22, 2026) - MGSM (Vals AI): 89.3% (source: Vals AI boards, read October 22, 2026) - SAGE (Vals AI): 30.4% (source: Vals AI boards, read October 22, 2026) - LegalBench (Vals AI): 50.1% (source: Vals AI boards, read October 22, 2026) - CaseLaw (Vals AI): 52.6% (source: Vals AI boards, read October 22, 2026) - TaxEval (Vals AI): 67.4% (source: Vals AI boards, read October 22, 2026) - MortgageTax (Vals AI): 53.6% (source: Vals AI boards, read October 22, 2026) - MedQA (Vals AI): 93.3% (source: Vals AI boards, read October 22, 2026) - MedCode (Vals AI): 30.4% (source: Vals AI boards, read October 22, 2026) - MedScribe (Vals AI): 72.9% (source: Vals AI boards, read October 22, 2026) - AA Math Index: 83.7 (source: Artificial Analysis, read October 22, 2026) - GPQA Diamond (Artificial Analysis run): 67.6% (source: Artificial Analysis, read October 22, 2026) - Humanity's Last Exam (Artificial Analysis run): 9.5% (source: Artificial Analysis, read October 22, 2026) - MMLU Pro (Artificial Analysis run): 78.0% (source: Artificial Analysis, read October 22, 2026) - LiveCodeBench (Artificial Analysis run): 78.9% (source: Artificial Analysis, read October 22, 2026) - Terminal-Bench Hard (Artificial Analysis run): 17.4% (source: Artificial Analysis, read October 22, 2026) - IFBench: 67.6% (source: Artificial Analysis, read October 22, 2026) - Long context reasoning (AA-LCR): 45.0% (source: Artificial Analysis, read October 22, 2026) - τ²-Bench Telecom: 36.5% (source: Artificial Analysis, read October 22, 2026) - AIME 2025 (Artificial Analysis run): 83.7% (source: Artificial Analysis, read October 22, 2026) - Terminal-Bench: 21.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - WeirdML: 38.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - GPQA Diamond (Epoch AI run): 69.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 20.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 2.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - Chess puzzles: 22.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Mystery game puzzles: 9.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 81.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tiers 1 to 3: 20.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tier 4: 2.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - ProofBench: 12.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - MATH level 5: 95.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleQA Verified: 11.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - DTBench: 62.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - LMCA: 7.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - Fiction.LiveBench: 44.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - VPCT: 37.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - Epoch Capabilities Index: 139.2 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1320 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1351 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1328 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1317 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1306 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: 1159 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1321 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1313 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1356 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1327 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1227 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1269 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1360 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1296 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1314 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1311 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1312 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1321 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1338 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1345 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1326 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1318 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1335 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1298 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1311 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1283 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1268 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1170 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1176 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1152 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1141 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1157 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: humor: 1110 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - Berkeley Function Calling Leaderboard (BFCL): 51.4% (source: Berkeley Function Calling Leaderboard, read October 22, 2026) - Kagi LLM Benchmark: 62.2% (source: Kagi LLM Benchmarking Project, read October 22, 2026)