# Google Gemini 2.5 Pro As of October 22, 2026, Google Gemini 2.5 Pro ranks #92 of 124 models overall with 41.8 ±16.2 on the LLMBenchmark Index. Gemini 2.5 Pro ranks #87 of 133 in web design, its strongest category. Google Gemini 2.5 Pro costs $1.25 per million input tokens and $10.00 per million output tokens. Gemini 2.5 Pro was released on June 17, 2025. Page: https://llmbenchmark.ai/models/gemini-2-5-pro Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: Google - Released: June 17, 2025 - Price per million input tokens: $1.25 - Price per million output tokens: $10.00 - Context window: 1.05M tokens - Overall rank: 92 of 124, by the LLMBenchmark Index - LLMBenchmark Index: 41.8 ±16.2 (90% margin, from 5 of 7 inputs) - Artificial Analysis Intelligence Index: 16.1 - Vibe Coding Index: 19.1 (from 3 of 6 coding benchmarks) Benchmark results (90 of 195): - SWE-bench Verified: 53.6% (source: SWE-bench (swebench.com), read October 22, 2026) - LMArena WebDev: 1226 Elo (source: LMArena WebDev, read October 22, 2026) - AA Intelligence Index: 16.1 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - AA Coding Index: 33.3 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - AA Agentic Index: 1.6 (source: Artificial Analysis (via OpenRouter), read October 22, 2026) - Design Arena: websites: 1167 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 1137 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 1111 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 1222 Elo (source: Design Arena, read October 22, 2026) - Design Arena: 3D: 1080 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 1152 Elo (source: Design Arena, read October 22, 2026) - SWE-bench Verified (Vals AI): 54.4% (source: Vals AI boards, read October 22, 2026) - Vibe Code Bench (Vals AI): 0.4% (source: Vals AI boards, read October 22, 2026) - SAGE (Vals AI): 41.9% (source: Vals AI boards, read October 22, 2026) - CaseLaw (Vals AI): 63.9% (source: Vals AI boards, read October 22, 2026) - CorpFin (Vals AI): 60.8% (source: Vals AI boards, read October 22, 2026) - MortgageTax (Vals AI): 68.9% (source: Vals AI boards, read October 22, 2026) - MedCode (Vals AI): 50.6% (source: Vals AI boards, read October 22, 2026) - MedScribe (Vals AI): 73.5% (source: Vals AI boards, read October 22, 2026) - AA Math Index: 87.7 (source: Artificial Analysis, read October 22, 2026) - GPQA Diamond (Artificial Analysis run): 84.4% (source: Artificial Analysis, read October 22, 2026) - Humanity's Last Exam (Artificial Analysis run): 22.5% (source: Artificial Analysis, read October 22, 2026) - MMLU Pro (Artificial Analysis run): 86.2% (source: Artificial Analysis, read October 22, 2026) - LiveCodeBench (Artificial Analysis run): 80.1% (source: Artificial Analysis, read October 22, 2026) - SciCode: 46.3% (source: Artificial Analysis, read October 22, 2026) - Terminal-Bench Hard (Artificial Analysis run): 26.5% (source: Artificial Analysis, read October 22, 2026) - IFBench: 48.7% (source: Artificial Analysis, read October 22, 2026) - Long context reasoning (AA-LCR): 69.0% (source: Artificial Analysis, read October 22, 2026) - τ²-Bench Telecom: 54.1% (source: Artificial Analysis, read October 22, 2026) - AIME 2025 (Artificial Analysis run): 87.7% (source: Artificial Analysis, read October 22, 2026) - Terminal-Bench: 32.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - GSO-Bench: 3.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - WeirdML: 54.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - GDPval: 23.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - DeepResearch Bench: 41.5% (source: Epoch AI benchmarking hub, read October 22, 2026) - GPQA Diamond (Epoch AI run): 85.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 41.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 4.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 84.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tiers 1 to 3: 24.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - FrontierMath, tier 4: 0.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - DTBench: 82.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - LMCA: 34.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - Creative writing (Lech Mazur): 83.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - Vending-Bench 2: $574 (source: Epoch AI benchmarking hub, read October 22, 2026) - Epoch Capabilities Index: 145.1 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1458 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1452 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1455 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1450 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1437 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: creative writing: 1454 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: 1263 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1458 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1452 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1507 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1487 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1461 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1434 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: French: 1473 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1474 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1461 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1479 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1453 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1449 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1452 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1453 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1459 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1454 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1480 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1476 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1480 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1439 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1454 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1441 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: HTML: 1235 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena WebDev: from an image: 1285 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1261 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1300 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1270 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1274 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1281 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: humor: 1262 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: captioning: 1304 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: recognizing things: 1283 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: creative writing: 1265 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Document: 1421 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - Kagi LLM Benchmark: 70.3% (source: Kagi LLM Benchmarking Project, read October 22, 2026) - BrowseComp-Plus: 29.5% (source: BrowseComp-Plus, read October 22, 2026) - FACTS Benchmark Suite: 61.5% (source: Kaggle Benchmarks, read October 22, 2026)