Gemini 2.5 Flash (Reasoning) vs Gemini 2.5 Flash Preview (Sep '25) (Reasoning)
Comparing 2 AI models · 6 benchmarks · Google
Most Affordable
Go
Gemini 2.5 Flash (Reasoning)
$0.30/1M
Highest Intelligence
Go
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)
79.3% GPQA
Best for Coding
Go
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)
42.5 Coding Index
Price Difference
1.0x
input cost range
Composite Indices
Intelligence, Coding, Math
Standard Benchmarks
Academic and industry benchmarks
Benchmark Winners
6 tests
Go
Gemini 2.5 Flash (Reasoning)
1
- MATH 500
Go
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)
5
- GPQA
- MMLU Pro
- HLE
- LiveCodeBench
- AIME 2025
| Metric | Go Gemini 2.5 Flash (Reasoning) | Go Gemini 2.5 Flash Preview (Sep '25) (Reasoning) |
|---|---|---|
| Pricing Per 1M tokens | ||
| Input Cost | $0.30/1M | $0.30/1M |
| Output Cost | $2.50/1M | $2.50/1M |
| Blended Cost 3:1 input/output ratio | $0.85/1M | $0.85/1M |
| Specifications | ||
| Organization Model creator | ||
| Release Date Launch date | May 20, 2025 | Sep 25, 2025 |
| Performance & Speed | ||
| Throughput Output speed | 299.0 tok/s | 155.2 tok/s |
| Time to First Token (TTFT) Initial response delay | 8658ms | 8247ms |
| Latency Time to first answer token | 8658ms | 8247ms |
| Composite Indices | ||
| Intelligence Index Overall reasoning capability | 51.2 | 54.4 |
| Coding Index Programming ability | 40.5 | 42.5 |
| Math Index Mathematical reasoning | 73.3 | 78.3 |
| Standard Benchmarks | ||
| GPQA Graduate-level reasoning | 79.0% | 79.3% |
| MMLU Pro Advanced knowledge | 83.2% | 84.2% |
| HLE Hard language evaluation | 11.1% | 12.7% |
| LiveCodeBench Real-world coding tasks | 69.5% | 71.3% |
| MATH 500 Mathematical problems | 98.1% | — |
| AIME 2025 Advanced math competition | 73.3% | 78.3% |
| AIME (Original) Math olympiad problems | 82.3% | — |
| SciCode Scientific code generation | 39.4% | 40.5% |
| LCR Code review capability | 61.7% | 64.3% |
| IFBench Instruction-following | 50.3% | 52.3% |
| TAU-bench v2 Tool use & agentic tasks | ||