# OpenAI o3 Mini As of October 21, 2026, OpenAI o3 Mini ranks #137 of 213 models overall with 12.5 on the Artificial Analysis Intelligence Index. Its strongest category is coding, where it ranks #73 of 136. OpenAI o3 Mini costs $1.10 per million input tokens and $4.40 per million output tokens. It was released on January 31, 2025. Page: https://llmbenchmark.ai/models/o3-mini Data from October 21, 2026. Every figure below names the board it was read from and the day. - Maker: OpenAI - Released: January 31, 2025 - Price per million input tokens: $1.10 - Price per million output tokens: $4.40 - Context window: 200K tokens - Overall rank: 137 of 213, by the Artificial Analysis Intelligence Index - Artificial Analysis Intelligence Index: 12.5 - Vibe Coding Index: 52.1 (from 2 of 4 coding benchmarks) Benchmark results (70 of 190): - Aider polyglot: 60.4% (source: Aider polyglot leaderboard, read October 21, 2026) - SWE-bench Verified: 42.4% (source: SWE-bench (swebench.com), read October 21, 2026) - SWE-bench Lite: 32.3% (source: SWE-bench (swebench.com), read October 21, 2026) - GPQA Diamond: 75.5% (source: GPQA (Vals AI), read October 21, 2026) - AIME: 86.5% (source: AIME (Vals AI), read October 21, 2026) - MMLU Pro: 78.7% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 12.5 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - LiveCodeBench (Vals AI): 71.5% (source: Vals AI boards, read October 21, 2026) - MATH 500 (Vals AI): 91.8% (source: Vals AI boards, read October 21, 2026) - MGSM (Vals AI): 91.3% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 71.5% (source: Vals AI boards, read October 21, 2026) - CorpFin (Vals AI): 45.3% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 69.4% (source: Vals AI boards, read October 21, 2026) - MedQA (Vals AI): 94.8% (source: Vals AI boards, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 77.3% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 12.0% (source: Artificial Analysis, read October 21, 2026) - MMLU Pro (Artificial Analysis run): 80.2% (source: Artificial Analysis, read October 21, 2026) - LiveCodeBench (Artificial Analysis run): 73.4% (source: Artificial Analysis, read October 21, 2026) - SciCode: 42.8% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench Hard (Artificial Analysis run): 6.8% (source: Artificial Analysis, read October 21, 2026) - IFBench: 67.1% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 43.0% (source: Artificial Analysis, read October 21, 2026) - τ²-Bench Telecom: 31.3% (source: Artificial Analysis, read October 21, 2026) - GSO-Bench: 1.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - WeirdML: 43.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 77.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI: 34.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI-2: 3.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleBench: 22.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - Chess puzzles: 15.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Mystery game puzzles: 7.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 76.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tiers 1 to 3: 18.6% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tier 4: 0.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - MATH level 5: 96.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleQA Verified: 15.3% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 68.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 19.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Fiction.LiveBench: 50.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Creative writing (Lech Mazur): 61.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - Cybench: 22.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - Epoch Capabilities Index: 140.2 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1337 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1378 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1365 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1396 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1337 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1286 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1351 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1319 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1379 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1303 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1286 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1313 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1334 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1321 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1304 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1294 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1320 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1343 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1364 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1375 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1364 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1399 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1339 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1330 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1328 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1313 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1313 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1283 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)