# OpenAI o3 As of October 21, 2026, OpenAI o3 ranks #101 of 213 models overall with 20.2 on the Artificial Analysis Intelligence Index. Its strongest category is coding, where it ranks #30 of 136. OpenAI o3 costs $2.00 per million input tokens and $8.00 per million output tokens. It was released on April 16, 2025. Page: https://llmbenchmark.ai/models/o3 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: $2.00 - Price per million output tokens: $8.00 - Context window: 200K tokens - Overall rank: 101 of 213, by the Artificial Analysis Intelligence Index - Artificial Analysis Intelligence Index: 20.2 - Vibe Coding Index: 70.7 (from 2 of 4 coding benchmarks) Benchmark results (97 of 190): - Aider polyglot: 81.3% (source: Aider polyglot leaderboard, read October 21, 2026) - SWE-bench Verified: 58.4% (source: SWE-bench (swebench.com), read October 21, 2026) - SWE-bench Multimodal: 36.0% (source: SWE-bench (swebench.com), read October 21, 2026) - GPQA Diamond: 84.1% (source: GPQA (Vals AI), read October 21, 2026) - AIME: 85.3% (source: AIME (Vals AI), read October 21, 2026) - MMLU Pro: 85.6% (source: MMLU Pro (Vals AI), read October 21, 2026) - AA Intelligence Index: 20.2 (source: Artificial Analysis (via OpenRouter), read October 21, 2026) - Design Arena: websites: 1036 Elo (source: Design Arena, read October 21, 2026) - Design Arena: UI components: 1016 Elo (source: Design Arena, read October 21, 2026) - Design Arena: game dev: 1034 Elo (source: Design Arena, read October 21, 2026) - Design Arena: data viz: 1200 Elo (source: Design Arena, read October 21, 2026) - Design Arena: all code categories: 1021 Elo (source: Design Arena, read October 21, 2026) - LiveCodeBench (Vals AI): 83.9% (source: Vals AI boards, read October 21, 2026) - MMMU Pro (Vals AI): 80.4% (source: Vals AI boards, read October 21, 2026) - MATH 500 (Vals AI): 94.6% (source: Vals AI boards, read October 21, 2026) - MGSM (Vals AI): 91.8% (source: Vals AI boards, read October 21, 2026) - SAGE (Vals AI): 41.8% (source: Vals AI boards, read October 21, 2026) - LegalBench (Vals AI): 83.8% (source: Vals AI boards, read October 21, 2026) - CorpFin (Vals AI): 59.7% (source: Vals AI boards, read October 21, 2026) - TaxEval (Vals AI): 74.6% (source: Vals AI boards, read October 21, 2026) - MortgageTax (Vals AI): 65.7% (source: Vals AI boards, read October 21, 2026) - MedQA (Vals AI): 96.1% (source: Vals AI boards, read October 21, 2026) - MedCode (Vals AI): 47.3% (source: Vals AI boards, read October 21, 2026) - MedScribe (Vals AI): 76.7% (source: Vals AI boards, read October 21, 2026) - AA Math Index: 88.3 (source: Artificial Analysis, read October 21, 2026) - GPQA Diamond (Artificial Analysis run): 82.7% (source: Artificial Analysis, read October 21, 2026) - Humanity's Last Exam (Artificial Analysis run): 20.1% (source: Artificial Analysis, read October 21, 2026) - MMLU Pro (Artificial Analysis run): 85.3% (source: Artificial Analysis, read October 21, 2026) - LiveCodeBench (Artificial Analysis run): 80.8% (source: Artificial Analysis, read October 21, 2026) - Terminal-Bench Hard (Artificial Analysis run): 37.1% (source: Artificial Analysis, read October 21, 2026) - IFBench: 71.4% (source: Artificial Analysis, read October 21, 2026) - Long context reasoning (AA-LCR): 74.7% (source: Artificial Analysis, read October 21, 2026) - τ²-Bench Telecom: 80.7% (source: Artificial Analysis, read October 21, 2026) - AIME 2025 (Artificial Analysis run): 88.3% (source: Artificial Analysis, read October 21, 2026) - GSO-Bench: 8.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - WeirdML: 52.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - METR time horizons: 65.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - GDPval: 30.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - DeepResearch Bench: 45.2% (source: Epoch AI benchmarking hub, read October 21, 2026) - GPQA Diamond (Epoch AI run): 81.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI: 60.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - ARC-AGI-2: 6.5% (source: Epoch AI benchmarking hub, read October 21, 2026) - SimpleBench: 53.1% (source: Epoch AI benchmarking hub, read October 21, 2026) - Chess puzzles: 37.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - Mystery game puzzles: 29.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - OTIS Mock AIME: 84.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - FrontierMath, tiers 1 to 3: 33.3% (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: 49.4% (source: Epoch AI benchmarking hub, read October 21, 2026) - GeoBench: 74.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - DTBench: 84.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - LMCA: 39.7% (source: Epoch AI benchmarking hub, read October 21, 2026) - Fiction.LiveBench: 88.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - Creative writing (Lech Mazur): 83.9% (source: Epoch AI benchmarking hub, read October 21, 2026) - CL-bench: 17.8% (source: Epoch AI benchmarking hub, read October 21, 2026) - OSWorld: 23.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - VPCT: 52.0% (source: Epoch AI benchmarking hub, read October 21, 2026) - ALE-Bench: 933.5 (source: ALE-Bench (Sakana AI), read October 21, 2026) - Epoch Capabilities Index: 146.7 (source: Epoch AI benchmarking hub, read October 21, 2026) - LMArena Text: 1410 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: coding: 1407 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts: 1402 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: math: 1426 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: instruction following: 1368 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: creative writing: 1359 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: 1214 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: English: 1417 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: non-English: 1401 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Chinese: 1437 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: German: 1420 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Japanese: 1403 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Korean: 1370 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: French: 1430 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Spanish: 1395 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Russian: 1406 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: Polish: 1438 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: multi-turn: 1405 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: longer queries: 1372 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: expert: 1402 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: hard prompts in English: 1411 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: software and IT: 1415 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: mathematical work: 1423 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: science: 1429 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: medicine and healthcare: 1448 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: legal and government: 1428 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: business and finance: 1393 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: writing and language: 1372 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Text: entertainment and media: 1373 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: English: 1221 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: Chinese: 1237 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: reading text: 1218 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: diagrams: 1220 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: 1222 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: captioning: 1210 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: recognizing things: 1234 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026) - LMArena Vision: creative writing: 1201 Elo (source: LMArena (Hugging Face dataset), read October 21, 2026)