readable AI benchmarks (simplified)
Google
Gemini 2.5 Flash Preview (Sep '25) (Reasoning)
Gemini 2.5 Flash Preview (Sep '25) (Reasoning) has a Quality Score of 23.7, ranking 185th among 238 scored models. It has a 1M token context window. Its Reliability Score is 31.9, ranking 195th among 245 scored models, below average (total average: 46.4).
Quality Score23.7coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability31.9
Cache Discountnot available
Model specification
- Reasoning
- reasoning
- Input modalities
- none
- Output modalities
- none
- Context window
- 1M tokens
- Weights
- closed weights
Token prices USD per 1M tokens
- Input
- not available
- Output
- not available
- Cached Input
- not available
- Cache write
- not available
- Cost per task
- not available
Capability
- Intelligence
- 15.5
- Omniscience (native net)
- -36.1
- Correct
- 28.3%
- Blended price
- not available
Answer outcomes
Fully graded outcomes (Correct + Incorrect): 92.8%
Correct 28.3%Incorrect 64.4%Partial / not attempted 7.2%
Artificial Analysis benchmarks legacy records
- Humanity’s Last Exam
- 14%
- GPQA Diamond
- 79%
- CritPt
- 0%
- AA-LCR
- 71%
Similar models
- Gemini 2.5 Flash (Reasoning)GoogleQuality Score 24.1Value Score 19.2
- Gemini 3.1 Flash-LiteGoogleQuality Score 28.7Value Score 24.0
- Gemini 2.5 Flash-Lite (Reasoning)GoogleQuality Score 17.9Value Score 16.5
- Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)GoogleQuality Score 16.7Value Score 15.4
- Gemini 3.5 Flash-LiteGoogleQuality Score 32.5Value Score 26.0
- Gemma 4 31B (Reasoning)GoogleQuality Score 15.1Value Score not available