# Google Gemini 2.5 Flash Lite

As of October 21, 2026, Google Gemini 2.5 Flash Lite ranks #153 of 213 models overall with 10.4 on the Artificial Analysis Intelligence Index. Its strongest category is knowledge, where it ranks #96 of 147. Google Gemini 2.5 Flash Lite costs $0.10 per million input tokens and $0.40 per million output tokens. It was released on July 22, 2025.

Page: https://llmbenchmark.ai/models/gemini-2-5-flash-lite
Data from October 21, 2026. Every figure below names the board it was read from and the day.

- Maker: Google
- Released: July 22, 2025
- Price per million input tokens: $0.10
- Price per million output tokens: $0.40
- Context window: 1.05M tokens
- Overall rank: 153 of 213, by the Artificial Analysis Intelligence Index
- Artificial Analysis Intelligence Index: 10.4

Benchmark results (28 of 190):

- GPQA Diamond: 70.2% (source: GPQA (Vals AI), read October 21, 2026)
- AIME: 42.1% (source: AIME (Vals AI), read October 21, 2026)
- MMLU Pro: 79.1% (source: MMLU Pro (Vals AI), read October 21, 2026)
- AA Intelligence Index: 10.4 (source: Artificial Analysis (via OpenRouter), read October 21, 2026)
- LiveCodeBench (Vals AI): 71.4% (source: Vals AI boards, read October 21, 2026)
- MMMU Pro (Vals AI): 75.4% (source: Vals AI boards, read October 21, 2026)
- MGSM (Vals AI): 89.5% (source: Vals AI boards, read October 21, 2026)
- SAGE (Vals AI): 30.8% (source: Vals AI boards, read October 21, 2026)
- LegalBench (Vals AI): 82.0% (source: Vals AI boards, read October 21, 2026)
- CorpFin (Vals AI): 57.6% (source: Vals AI boards, read October 21, 2026)
- TaxEval (Vals AI): 66.2% (source: Vals AI boards, read October 21, 2026)
- MortgageTax (Vals AI): 57.6% (source: Vals AI boards, read October 21, 2026)
- MedQA (Vals AI): 88.9% (source: Vals AI boards, read October 21, 2026)
- MedCode (Vals AI): 34.2% (source: Vals AI boards, read October 21, 2026)
- MedScribe (Vals AI): 75.8% (source: Vals AI boards, read October 21, 2026)
- AA Math Index: 53.3 (source: Artificial Analysis, read October 21, 2026)
- GPQA Diamond (Artificial Analysis run): 62.5% (source: Artificial Analysis, read October 21, 2026)
- Humanity's Last Exam (Artificial Analysis run): 6.8% (source: Artificial Analysis, read October 21, 2026)
- MMLU Pro (Artificial Analysis run): 75.9% (source: Artificial Analysis, read October 21, 2026)
- LiveCodeBench (Artificial Analysis run): 59.3% (source: Artificial Analysis, read October 21, 2026)
- Terminal-Bench Hard (Artificial Analysis run): 4.5% (source: Artificial Analysis, read October 21, 2026)
- IFBench: 49.9% (source: Artificial Analysis, read October 21, 2026)
- Long context reasoning (AA-LCR): 55.7% (source: Artificial Analysis, read October 21, 2026)
- τ²-Bench Telecom: 19.0% (source: Artificial Analysis, read October 21, 2026)
- AIME 2025 (Artificial Analysis run): 53.3% (source: Artificial Analysis, read October 21, 2026)
- DTBench: 62.8% (source: Epoch AI benchmarking hub, read October 21, 2026)
- LMCA: 18.1% (source: Epoch AI benchmarking hub, read October 21, 2026)
- Epoch Capabilities Index: 133.8 (source: Epoch AI benchmarking hub, read October 21, 2026)