Gemini 2.5 Flash Preview (Reasoning) vs Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
Comparing 2 AI models · 6 benchmarks · Google
Most Affordable
Go
Gemini 2.5 Flash Preview (Reasoning)
$0.00/1M
Highest Intelligence
Go
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
70.9% GPQA
Best for Coding
Go
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
36.5 Coding Index
Price Difference
Infinityx
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
6 tests
Go
Gemini 2.5 Flash Preview (Reasoning)
2
- HLE
- MATH 500
Go
Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)
4
- GPQA
- MMLU Pro
- LiveCodeBench
- AIME 2025
| Metric | Go Gemini 2.5 Flash Preview (Reasoning) | Go Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $0.00/1M | $0.10/1M |
| Output Cost | $0.00/1M | $0.40/1M |
| Blended Cost 3:1 input/output ratio | — | $0.18/1M |
| Specifications | ||
| Organization Model creator | ||
| Release Date Launch date | Apr 17, 2025 | Sep 8, 2025 |
| Performance & Speed | ||
| Throughput Output speed | — | 5.3 tok/s |
| Time to First Token (TTFT) Initial response delay | — | 3556ms |
| Latency Time to first answer token | — | 3556ms |
| Composite Indices | ||
| Intelligence Index Overall reasoning capability | 45.8 | 47.9 |
| Coding Index Programming ability | — | 36.5 |
| Math Index Mathematical reasoning | — | 68.7 |
| Standard Benchmarks | ||
| GPQA Graduate-level reasoning | 69.8% | 70.9% |
| MMLU Pro Advanced knowledge | 80.0% | 80.8% |
| HLE Hard language evaluation | 11.6% | 6.6% |
| LiveCodeBench Real-world coding tasks | 50.5% | 68.8% |
| MATH 500 Mathematical problems | 98.1% | — |
| AIME 2025 Advanced math competition | — | 68.7% |
| AIME (Original) Math olympiad problems | 84.3% | — |
| SciCode Scientific code generation | 35.9% | 28.7% |
| LCR Code review capability | — | 59.0% |
| IFBench Instruction-following | — | 52.6% |
| TAU-bench v2 Tool use & agentic tasks | — | 30.7% |
| TerminalBench Hard CLI command generation | — | 12.1% |
Key Takeaways
Gemini 2.5 Flash Preview (Reasoning) offers the best value at $0.00/1M, making it ideal for high-volume applications and cost-conscious projects.