# OpenAI GPT-4.1 As of October 22, 2026, OpenAI GPT-4.1 ranks #104 of 123 models overall with 36.5 ±12.3 on the LLMBenchmark Index. GPT-4.1 ranks #100 of 122 in reasoning, its strongest category. OpenAI GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens. GPT-4.1 was released on April 14, 2025. Page: https://llmbenchmark.ai/models/gpt-4-1 Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: OpenAI - Released: April 14, 2025 - Price per million input tokens: $2.00 - Price per million output tokens: $8.00 - Context window: 1.05M tokens - Overall rank: 104 of 123, by the LLMBenchmark Index - LLMBenchmark Index: 36.5 ±12.3 (90% margin, from 5 of 7 inputs) - Artificial Analysis Intelligence Index: 12.7 Benchmark results (92 of 195): - Aider polyglot: 52.4% (source: Aider polyglot leaderboard, read October 22, 2026) - SWE-bench Verified: 39.6% (source: SWE-bench (swebench.com), read October 22, 2026) - SWE-bench Multimodal: 31.1% (source: SWE-bench (swebench.com), read October 22, 2026) - GPQA Diamond: 65.4% (source: GPQA (Vals AI), read October 22, 2026) - AIME: 39.6% (source: AIME (Vals AI), read October 22, 2026) - MMLU Pro: 80.5% (source: MMLU Pro (Vals AI), read October 22, 2026) - AA Intelligence Index: 12.7 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - Design Arena: websites: 1038 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 997 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 1079 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 1104 Elo (source: Design Arena, read October 22, 2026) - Design Arena: 3D: 849 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 1025 Elo (source: Design Arena, read October 22, 2026) - LiveCodeBench (Vals AI): 54.7% (source: Vals AI boards, read October 22, 2026) - MMMU Pro (Vals AI): 72.4% (source: Vals AI boards, read October 22, 2026) - MATH 500 (Vals AI): 87.2% (source: Vals AI boards, read October 22, 2026) - MGSM (Vals AI): 87.7% (source: Vals AI boards, read October 22, 2026) - LegalBench (Vals AI): 83.1% (source: Vals AI boards, read October 22, 2026) - CaseLaw (Vals AI): 69.9% (source: Vals AI boards, read October 22, 2026) - CorpFin (Vals AI): 63.0% (source: Vals AI boards, read October 22, 2026) - TaxEval (Vals AI): 75.1% (source: Vals AI boards, read October 22, 2026) - MortgageTax (Vals AI): 65.9% (source: Vals AI boards, read October 22, 2026) - MedQA (Vals AI): 91.2% (source: Vals AI boards, read October 22, 2026) - AA Math Index: 34.7 (source: Artificial Analysis, read October 22, 2026) - GPQA Diamond (Artificial Analysis run): 66.6% (source: Artificial Analysis, read October 22, 2026) - Humanity's Last Exam (Artificial Analysis run): 4.2% (source: Artificial Analysis, read October 22, 2026) - MMLU Pro (Artificial Analysis run): 80.6% (source: Artificial Analysis, read October 22, 2026) - LiveCodeBench (Artificial Analysis run): 45.7% (source: Artificial Analysis, read October 22, 2026) - Terminal-Bench Hard (Artificial Analysis run): 13.6% (source: Artificial Analysis, read October 22, 2026) - IFBench: 43.0% (source: Artificial Analysis, read October 22, 2026) - Long context reasoning (AA-LCR): 68.3% (source: Artificial Analysis, read October 22, 2026) - τ²-Bench Telecom: 47.1% (source: Artificial Analysis, read October 22, 2026) - AIME 2025 (Artificial Analysis run): 34.7% (source: Artificial Analysis, read October 22, 2026) - WeirdML: 39.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - GPQA Diamond (Epoch AI run): 66.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 5.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 0.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleBench: 27.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Chess puzzles: 3.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 38.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tiers 1 to 3: 6.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - MATH level 5: 83.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleQA Verified: 31.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - GeoBench: 72.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - DTBench: 68.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - LMCA: 25.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - Fiction.LiveBench: 63.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - ALE-Bench: 558.1 (source: ALE-Bench (Sakana AI), read October 22, 2026) - Epoch Capabilities Index: 136.7 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1383 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1390 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1384 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1369 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1367 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: creative writing: 1363 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: 1210 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1392 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1370 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1382 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1381 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1319 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1338 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: French: 1382 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1376 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1377 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1389 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1397 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1385 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1364 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1393 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1391 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1360 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1382 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1379 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1399 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1369 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1371 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1365 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1209 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1226 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1218 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1215 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1248 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: humor: 1196 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: captioning: 1207 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: recognizing things: 1208 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: creative writing: 1210 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - Berkeley Function Calling Leaderboard (BFCL): 54.0% (source: Berkeley Function Calling Leaderboard, read October 22, 2026) - Kagi LLM Benchmark: 52.3% (source: Kagi LLM Benchmarking Project, read October 22, 2026) - BrowseComp-Plus: 36.4% (source: BrowseComp-Plus, read October 22, 2026) - SciCode: 4.6% (source: Kaggle Benchmarks, read October 22, 2026) - FACTS Benchmark Suite: 45.8% (source: Kaggle Benchmarks, read October 22, 2026)