Gemini 2.5 Flash Lite Preview 09 2025 — Retired model
Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token generation, and better performance...
Technical specifications
Independent benchmarks
Scores below come from Artificial Analysis, an independent third party. BazaarLink does not participate in the testing.
Intelligence 13
Coding
Math 47
MMLU 80
GPQA 65
This modelCategory leader
Overall intelligence
#317out of 573 models
Aggregated across academic benchmarks
Math reasoning
#145out of 269 models
AIME / MATH-500 / SciCode
Time to first token
🥇
#1out of 586 models
AA 全球 p50：0.00 秒
Intelligence
13
Mid-tierThis model13
Category leader61
Median15
Math
47
Mid-tierThis model47
Category leader99
Median53
MMLU Pro
80%
—This model80%
Category leader90%
Median75%
GPQA
65%
—This model65%
Category leader94%
Median69%
LiveCodeBench
64%
—This model64%
Category leader42%
Median42%
HLE
5%
—This model5%
Category leader53%
Median7%
SciCode
28%
—This model28%
Category leader60%
Median33%
IFBench
42%
—This model42%
Category leader83%
Median44%
τ²-Bench Telecom
30%
—This model30%
Category leader99%
Median46%
AA-LCR
48%
—This model48%
Category leader76%
Median40%
Terminal-Bench Hard
8%
—This model8%
Category leader66%
Median14%
Top 5 — CodingCoding Index leaderboard
1GPT-5.6 Sol (xhigh)
openai/gpt-5-6-sol-xhigh78$5 / $304GPT-5.6 Sol (high)
openai/gpt-5-6-sol-high77$5 / $305Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)
anthropic/claude-opus-5-xhigh77$5 / $25AASource: Artificial Analysis · Independent third-party evaluation; not influenced by BazaarLinkView full evaluation on AA →
Frequently Asked Questions
Can I still use the retired Gemini 2.5 Flash Lite Preview 09 2025 model?
No. Gemini 2.5 Flash Lite Preview 09 2025 has been retired and is retained here only as a historical reference. See the active alternatives linked on this page.
Relay integrity checks
No integrity-check data is available for this model yet.
BazaarLink Probe verifies endpoints that claim to serve this model and flags behavior that differs from the reference baseline.
View the full integrity report →Related models and links
More from this provider: Google