# Google Gemini 2.5 Flash

As of October 22, 2026, Google Gemini 2.5 Flash ranks #107 of 123 models overall with 34.3 ±24.0 on the LLMBenchmark Index. Gemini 2.5 Flash ranks #112 of 133 in web design, its strongest category. Google Gemini 2.5 Flash costs $0.30 per million input tokens and $2.50 per million output tokens. Gemini 2.5 Flash was released on June 17, 2025.

Page: https://llmbenchmark.ai/models/gemini-2-5-flash
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: $0.30
- Price per million output tokens: $2.50
- Context window: 1.05M tokens
- Overall rank: 107 of 123, by the LLMBenchmark Index
- LLMBenchmark Index: 34.3 ±24.0 (90% margin, from 3 of 7 inputs)
- Artificial Analysis Intelligence Index: 15.5

Benchmark results (73 of 195):

- SWE-bench Verified: 28.7% (source: SWE-bench (swebench.com), read October 22, 2026)
- AA Intelligence Index: 15.5 (source: Artificial Analysis (via OpenRouter), read October 22, 2026)
- Design Arena: websites: 1074 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: UI components: 1002 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: game dev: 1004 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: data viz: 1060 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: 3D: 1020 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: all code categories: 1059 Elo (source: Design Arena, read October 22, 2026)
- Design Arena: SVG: 1020 Elo (source: Design Arena, read October 22, 2026)
- SAGE (Vals AI): 44.8% (source: Vals AI boards, read October 22, 2026)
- MedCode (Vals AI): 40.4% (source: Vals AI boards, read October 22, 2026)
- MedScribe (Vals AI): 83.0% (source: Vals AI boards, read October 22, 2026)
- AA Math Index: 73.3 (source: Artificial Analysis, read October 22, 2026)
- GPQA Diamond (Artificial Analysis run): 79.0% (source: Artificial Analysis, read October 22, 2026)
- Humanity's Last Exam (Artificial Analysis run): 12.1% (source: Artificial Analysis, read October 22, 2026)
- MMLU Pro (Artificial Analysis run): 83.2% (source: Artificial Analysis, read October 22, 2026)
- LiveCodeBench (Artificial Analysis run): 69.5% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 13.6% (source: Artificial Analysis, read October 22, 2026)
- IFBench: 50.3% (source: Artificial Analysis, read October 22, 2026)
- Long context reasoning (AA-LCR): 65.3% (source: Artificial Analysis, read October 22, 2026)
- τ²-Bench Telecom: 31.6% (source: Artificial Analysis, read October 22, 2026)
- AIME 2025 (Artificial Analysis run): 73.3% (source: Artificial Analysis, read October 22, 2026)
- Terminal-Bench: 17.1% (source: Epoch AI benchmarking hub, read October 22, 2026)
- BALROG: 33.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI: 33.3% (source: Epoch AI benchmarking hub, read October 22, 2026)
- ARC-AGI-2: 2.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- SimpleBench: 41.2% (source: Epoch AI benchmarking hub, read October 22, 2026)
- DTBench: 76.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMCA: 27.5% (source: Epoch AI benchmarking hub, read October 22, 2026)
- Vending-Bench 2: $549 (source: Epoch AI benchmarking hub, read October 22, 2026)
- Epoch Capabilities Index: 142.9 (source: Epoch AI benchmarking hub, read October 22, 2026)
- LMArena Text: 1417 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: coding: 1423 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts: 1422 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: math: 1411 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: instruction following: 1405 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: creative writing: 1400 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: 1235 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: English: 1418 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: non-English: 1409 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Chinese: 1449 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: German: 1417 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Japanese: 1396 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Korean: 1385 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: French: 1432 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Spanish: 1422 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Russian: 1415 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: Polish: 1413 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: multi-turn: 1408 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: longer queries: 1419 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: expert: 1426 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: hard prompts in English: 1420 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: software and IT: 1425 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: mathematical work: 1422 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: science: 1433 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: medicine and healthcare: 1428 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: legal and government: 1430 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: business and finance: 1404 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: writing and language: 1405 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Text: entertainment and media: 1393 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: English: 1239 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: Chinese: 1284 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: reading text: 1237 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: diagrams: 1245 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: homework: 1244 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: humor: 1225 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: captioning: 1277 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: recognizing things: 1252 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- LMArena Vision: creative writing: 1241 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026)
- Berkeley Function Calling Leaderboard (BFCL): 56.2% (source: Berkeley Function Calling Leaderboard, read October 22, 2026)
- Kagi LLM Benchmark: 56.8% (source: Kagi LLM Benchmarking Project, read October 22, 2026)
- BrowseComp-Plus: 39.9% (source: BrowseComp-Plus, read October 22, 2026)
- FACTS Benchmark Suite: 47.2% (source: Kaggle Benchmarks, read October 22, 2026)