# OpenAI GPT-5.5

As of October 22, 2026, OpenAI GPT-5.5 ranks #14 of 123 models overall with 69.2 ±7.7 on the LLMBenchmark Index. GPT-5.5 ranks #14 of 122 in reasoning, its strongest category. OpenAI GPT-5.5 costs $5.00 per million input tokens and $30.00 per million output tokens. GPT-5.5 was released on April 24, 2026.

Page: https://llmbenchmark.ai/models/gpt-5-5
Data from October 22, 2026. Every figure below names the board it was read from and the day.

- Maker: OpenAI
- Released: April 24, 2026
- Price per million input tokens: $5.00
- Price per million output tokens: $30.00
- Context window: 1.05M tokens
- Overall rank: 14 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 69.2 ±7.7 (90% margin, from 7 of 7 inputs)
- Artificial Analysis Intelligence Index: 38.4
- Vibe Coding Index: 71.3 (from 5 of 6 coding benchmarks)

Benchmark results (134 of 195):

- LiveBench coding: 85.1% (source: LiveBench, read October 22, 2026)
- LMArena WebDev: 1513 Elo (source: LMArena WebDev, read October 22, 2026)
- GPQA Diamond: 93.2% (source: GPQA (Vals AI), read October 22, 2026)
- MMLU Pro: 88.1% (source: MMLU Pro (Vals AI), read October 22, 2026)
- AA Intelligence Index: 38.4 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Coding Index: 74.9 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- AA Agentic Index: 36.4 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- Design Arena: websites: 1256 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: UI components: 1257 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: game dev: 1293 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: data viz: 1264 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: 3D: 1197 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: all code categories: 1260 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: SVG: 1234 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: ASCII art: 1255 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building web apps: 1117 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building full-stack apps: 1089 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building mobile apps: 1142 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building Android apps: 1164 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building Godot games: 1173 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: agents building games: 1179 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: HTML slides: 1017 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: PowerPoint slides: 1084 Elo (source: Design Arena, read October 22, 2026)
- LiveBench reasoning: 89.7% (source: LiveBench, read October 22, 2026)
- LiveBench data analysis: 81.6% (source: LiveBench, read October 22, 2026)
- LiveBench research: 61.6% (source: LiveBench, read October 22, 2026)
- LiveBench browser: 48.0% (source: LiveBench, read October 22, 2026)
- LiveBench long agentic: 44.6% (source: LiveBench, read October 22, 2026)
- LiveBench design: 70.3% (source: LiveBench, read October 22, 2026)
- LiveCodeBench (Vals AI): 85.3% (source: Vals AI boards, read October 22, 2026)
- SWE-bench Verified (Vals AI): 82.6% (source: Vals AI boards, read October 22, 2026)
- Vibe Code Bench (Vals AI): 69.8% (source: Vals AI boards, read October 22, 2026)
- Code migration (Vals AI): 45.2% (source: Vals AI boards, read October 22, 2026)
- ProgramBench (Vals AI): 0.5% (source: Vals AI boards, read October 22, 2026)
- SREBench (Vals AI): 3.8% (source: Vals AI boards, read October 22, 2026)
- Terminal-Bench 2.1 (Vals AI): 76.4% (source: Vals AI boards, read October 22, 2026)
- SkillsBench (Vals AI): 62.5% (source: Vals AI boards, read October 22, 2026)
- Finance Agent (Vals AI): 51.8% (source: Vals AI boards, read October 22, 2026)
- Tax Agent Bench (Vals AI): 21.8% (source: Vals AI boards, read October 22, 2026)
- Legal Research Bench (Vals AI): 40.4% (source: Vals AI boards, read October 22, 2026)
- Excel Modeling Benchmark (Vals AI): 64.5% (source: Vals AI boards, read October 22, 2026)
- Time Horizon Index (Vals AI): 8.3% (source: Vals AI boards, read October 22, 2026)
- Public Benefits Bench (Vals AI): 60.9% (source: Vals AI boards, read October 22, 2026)
- MMMU Pro (Vals AI): 88.3% (source: Vals AI boards, read October 22, 2026)
- SAGE (Vals AI): 51.5% (source: Vals AI boards, read October 22, 2026)
- LegalBench (Vals AI): 86.5% (source: Vals AI boards, read October 22, 2026)
- CaseLaw (Vals AI): 66.2% (source: Vals AI boards, read October 22, 2026)
- CorpFin (Vals AI): 68.4% (source: Vals AI boards, read October 22, 2026)
- TaxEval (Vals AI): 75.0% (source: Vals AI boards, read October 22, 2026)
- MortgageTax (Vals AI): 68.8% (source: Vals AI boards, read October 22, 2026)
- MedCode (Vals AI): 49.1% (source: Vals AI boards, read October 22, 2026)
- MedScribe (Vals AI): 86.9% (source: Vals AI boards, read October 22, 2026)
- Vals Multimodal Index: 68.1% (source: Vals AI boards, read October 22, 2026)
- GPQA Diamond (Artificial Analysis run): 93.5% (source: Artificial Analysis, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 45.8% (source: Artificial Analysis, read October 22, 2026)
- SciCode: 56.1% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 60.6% (source: Artificial Analysis, read October 22, 2026)
- IFBench: 75.9% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 84.3% (source: Artificial Analysis, read October 22, 2026)
- τ²-Bench Telecom: 93.9% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench: 84.7% (source: Epoch AI benchmarking hub, read October 22, 2026)
- FrontierCode: 43.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- GSO-Bench: 40.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- WeirdML: 84.9% (source: Epoch AI benchmarking hub, read October 22, 2026)
- MirrorCode: 10.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- APEX-Agents: 55.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Remote Labor Index: 6.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OSWorld 2.0: 13.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- DeepResearch Bench: 54.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- PostTrainBench: 27.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- GPQA Diamond (Epoch AI run): 90.7% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI: 95.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI-2: 85.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleBench: 69.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Chess puzzles: 63.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Mystery game puzzles: 56.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- EBR-bench: 34.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- OTIS Mock AIME: 84.4% (source: Epoch AI benchmarking hub, read October 22, 2026)
- FrontierMath, tiers 1 to 3: 85.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- FrontierMath, tier 4: 72.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ProofBench: 50.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleQA Verified: 63.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- DTBench: 96.0% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMCA: 54.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Surface Evolver Bench: 88.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Furniture assembly: 44.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ExploitBench: 47.4% (source: Epoch AI benchmarking hub, read October 22, 2026)
- CL-bench Life: 22.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ALE-Bench: 1943.0 (source: ALE-Bench (Sakana AI), read October 22, 2026)
- Vending-Bench 2: $7,524 (source: Epoch AI benchmarking hub, read October 22, 2026)
- Epoch Capabilities Index: 159.7 (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1471 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1494 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1489 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1487 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1478 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1455 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: 1297 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1470 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1467 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 1534 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: German: 1480 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Japanese: 1499 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Korean: 1460 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: French: 1485 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Spanish: 1468 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1473 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Polish: 1465 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1476 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1484 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1507 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1483 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1493 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1496 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1485 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1465 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1491 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1478 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1466 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1449 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: React: 1506 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: HTML: 1543 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena WebDev: from an image: 1532 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: English: 1292 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: Chinese: 1360 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: reading text: 1306 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: diagrams: 1325 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: homework: 1332 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: humor: 1293 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: recognizing things: 1231 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: creative writing: 1301 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Document: 1486 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- Kagi LLM Benchmark: 88.8% (source: Kagi LLM Benchmarking Project, read October 22, 2026)
- FACTS Benchmark Suite: 66.7% (source: Kaggle Benchmarks, read October 22, 2026)