# OpenAI o4 Mini As of October 21, 2026, OpenAI o4 Mini ranks #113 of 213 models overall with 16.7 on the Artificial Analysis Intelligence Index. Its strongest category is coding, where it ranks #35 of 136. OpenAI o4 Mini costs $1.10 per million input tokens and $4.40 per million output tokens. It was released on April 16, 2025. Page: https://llmbenchmark.ai/models/o4-mini Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: OpenAI - Released: April 16, 2025 - Price per million input tokens: $1.10 - Price per million output tokens: $4.40 - Context window: 200K tokens - Overall rank: 113 of 213, by the Artificial Analysis Intelligence Index - Artificial Analysis Intelligence Index: 16.7 - Vibe Coding Index: 68.6 (from 2 of 4 coding benchmarks) Benchmark results (94 of 190): - Aider polyglot: 72.0% (source: Aider polyglot leaderboard, read October 21, 2026) - SWE-bench Verified: 64.6% (source: SWE-bench (swebench.com), read October 21, 2026) - SWE-bench Multimodal: 33.9% (source: SWE-bench (swebench.com), read October 21, 2026) - GPQA Diamond: 74.5% (source: GPQA (Vals AI), read October 21, 2026) - AIME: 83.7% (source: AIME (Vals AI), read October 21, 2026) - MMLU Pro: 80.6% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 16.7 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 985 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 983 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1004 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 990 Elo (source: Design Arena, read October 21, 2026) - Design Arena: 3D: 854 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 977 Elo (source: Design Arena, read October 21, 2026) - LiveCodeBench (Vals AI): 82.2% (source: Vals AI boards, read October 21, 2026) - MMMU Pro (Vals AI): 79.7% (source: Vals AI boards, read October 21, 2026) - MATH 500 (Vals AI): 94.2% (source: Vals AI boards, read October 21, 2026) - MGSM (Vals AI): 93.4% (source: Vals AI boards, read October 21, 2026) - SAGE (Vals AI): 41.1% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 79.2% (source: Vals AI boards, read October 21, 2026) - CorpFin (Vals AI): 59.0% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 74.8% (source: Vals AI boards, read October 21, 2026) - MortgageTax (Vals AI): 64.8% (source: Vals AI boards, read October 21, 2026) - MedQA (Vals AI): 96.0% (source: Vals AI boards, read October 21, 2026) - MedCode (Vals AI): 33.8% (source: Vals AI boards, read October 21, 2026) - MedScribe (Vals AI): 69.1% (source: Vals AI boards, read October 21, 2026) - AA Math Index: 90.7 (source: Artificial Analysis, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 78.4% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 16.5% (source: Artificial Analysis, read October 21, 2026) - MMLU Pro (Artificial Analysis run): 83.2% (source: Artificial Analysis, read October 21, 2026) - LiveCodeBench (Artificial Analysis run): 85.9% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench Hard (Artificial Analysis run): 15.2% (source: Artificial Analysis, read October 21, 2026) - IFBench: 68.7% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 61.0% (source: Artificial Analysis, read October 21, 2026) - τ²-Bench Telecom: 55.6% (source: Artificial Analysis, read October 21, 2026) - AIME 2025 (Artificial Analysis run): 90.7% (source: Artificial Analysis, read October 21, 2026) - GSO-Bench: 3.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - WeirdML: 52.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - METR time horizons: 63.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 79.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI: 58.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI-2: 6.1% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleBench: 38.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - Chess puzzles: 22.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Mystery game puzzles: 5.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 81.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tiers 1 to 3: 36.1% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tier 4: 4.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - MATH level 5: 97.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleQA Verified: 19.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - GeoBench: 64.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 77.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 26.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - Fiction.LiveBench: 77.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - Creative writing (Lech Mazur): 75.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - VPCT: 57.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 145.5 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1353 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1368 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1351 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1389 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1320 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1294 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: 1194 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1367 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1337 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1354 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1336 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1308 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1312 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1364 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1346 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1334 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1358 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1350 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1315 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1343 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1366 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1367 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1379 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1354 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1361 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1350 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1325 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1316 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1308 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: English: 1200 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: Chinese: 1218 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: reading text: 1197 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: diagrams: 1197 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: homework: 1234 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: humor: 1199 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: captioning: 1204 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: recognizing things: 1218 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: creative writing: 1166 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)