GoogleGemini 2.5 Flash Lite 09
Gemini 2.5 Flash Lite 09 is a Google proprietary reasoning model, released 25 Sept 2025. Its best configuration (thinking reasoning effort) ranks #443 of 785 on the BenchLeader Index at 47.9 ±3.0, in the lower half. The ± is the point: 290 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in long context (57) and lowest in reasoning (41). At $0.175 per million tokens blended it is among the cheapest fifth of ranked models. It has been measured at 3 reasoning-effort settings; this summary describes the best-scoring one, and the tabs above switch between them. Last measured 13 Oct 2026.
- Blended price
- $0.175/M
- $0.100 in · $0.400 out
- Output speed
- –
- First answer
- –
- Context
- 1M
- Full answer
- –
- Cost per run
- –
- Released
- 25 Sept 2025
- Overall index48
- Reasoning41
- Coding51
- Agents & tools45
- Maths45
- Knowledge46
- Instruction following54
- Multimodal48
- Long context57
- Composite41
Versions
Google has shipped 6 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.
| Model | Released | Index | Rank |
|---|---|---|---|
| Gemini 3.5 Flash Lite | 21 Jul 2026 | 54.4 | #253 |
| Gemini 3.1 Flash Lite | 3 Mar 2026 | 53.7 | #274 |
| Gemini 2.5 Flash Lite 09thinkingthis page | 25 Sept 2025 | 47.9 | #443 |
| Gemini 2.5 Flash-Lite | 17 Jun 2025 | 48.3 | #432 |
| Gemini 2.0 Flash Lite 001 | 25 Feb 2025 | – | – |
| Gemini 2.0 Flash-Lite | 5 Feb 2025 | 47.2 | #462 |
Reasoning-effort configurations
The same model behaves differently depending on how much it is allowed to think. Each row is one setting, scored only on the benchmarks that were run at that setting. “Not stated” collects results from publishers that did not say which setting they used; for a reasoning model that is usually its thinking mode, but we do not assume it. Pick a setting here or at the top of the page to see its price, speed and category scores.
| Effort | Index | Rank | Speed | First answer | Chat reply cost | Categories |
|---|---|---|---|---|---|---|
| no reasoning | 45.3 | #519 | – | – | $0.0002 | Agents & tools 40 · Composite 40 · Instruction following 44 · Knowledge 42 · Long context 49 · Multimodal 46 · Reasoning 41 |
| thinkingbest | 47.9 | #443 | – | – | $0.0002 | Agents & tools 45 · Coding 51 · Composite 41 · Instruction following 54 · Knowledge 46 · Long context 57 · Maths 45 · Multimodal 48 · Reasoning 41 |
| not stated | 46.9 | #471 | – | – | – | Coding 48 · Knowledge 47 · Maths 42 |
How its index has moved
9 Sept 2026 to 21 Oct 2026- thinking
- not stated
- no reasoning
The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | no reasoning | thinking | not stated | Source |
|---|---|---|---|---|
| GPQA Diamond (AA)not in index | 65.0%#344 | 70.9%#291 | – | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 5.1%#446 | 7.0%#375 | – | Artificial Analysis |
| GPQA Diamond (Vals)not in index | – | 70.2%#88 | 64.1%#100 | Vals AI |
| CritPt | 0.0%#315 | 0.0%#315 | – | Artificial Analysis |
Coding
| Benchmark | thinking | not stated | Source |
|---|---|---|---|
| LiveCodeBench | 71.4%#83 | 67.7%#92 | Vals AI |
Agents & tools
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| Terminal-Bench Hard | 7.6%#241 | 12.9%#206 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 30.4%#258 | 30.7%#255 | Artificial Analysis |
Maths
| Benchmark | thinking | not stated | Source |
|---|---|---|---|
| AIME (Vals) | 42.1%#65 | 26.3%#74 | Vals AI |
| MGSM | 88.4%#49 | 89.5%#42 | Vals AI |
Knowledge
| Benchmark | no reasoning | thinking | not stated | Source |
|---|---|---|---|---|
| AA-Omniscience | -42.6#336 | -54.0#423 | – | Artificial Analysis |
| MMLU-Pro | – | 79.1%#94 | 78.6%#97 | Vals AI |
| LegalBench | – | 82.0%#76 | 79.0%#97 | Vals AI |
| CorpFin | – | 57.6%#85 | 56.3%#88 | Vals AI |
| TaxEval | – | 64.7%#112 | 66.2%#110 | Vals AI |
| MedQA | – | 88.9%#51 | 80.3%#69 | Vals AI |
| MedCodenot in index | – | 34.2%#78 | 27.1%#99 | Vals AI |
| MedScribenot in index | – | 66.9%#96 | 75.8%#77 | Vals AI |
| AA-Omniscience: accuracynot in index | 14.2%#442 | 18.0%#349 | – | Artificial Analysis |
| AA-Omniscience: non-hallucinationnot in index | 33.9%#196 | 12.2%#378 | – | Artificial Analysis |
Instruction following
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| IFBench | 41.8%#242 | 52.6%#160 | Artificial Analysis |
Multimodal
| Benchmark | no reasoning | thinking | not stated | Source |
|---|---|---|---|---|
| MMMU-Pro | 63.4%#189 | 65.0%#178 | – | Artificial Analysis |
| MMMU-Pro (Vals)not in index | – | 75.4%#53 | 72.5%#61 | Vals AI |
| MortgageTaxnot in index | – | 57.5%#70 | 55.8%#74 | Vals AI |
| SAGEnot in index | – | 30.8%#77 | 28.0%#83 | Vals AI |
| VPCTnot in indexeffort not stated | – | – | 30.0%#30 | Epoch AI Benchmarking Hub |
Long context
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| AA-LCR | 49.7%#325 | 64.7%#255 | Artificial Analysis |
Composite
| Benchmark | no reasoning | thinking | Source |
|---|---|---|---|
| AA Intelligence Index v4.3.2 | 9.3#402 | 10.3#379 | Artificial Analysis |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0002 | – | – |
| Summarize a 30-page report | 12,000 / 600 | $0.0014 | – | – |
| Code edit | 6,000 / 1,500 | $0.0012 | – | – |
| Agentic coding session | 60,000 / 4,000 | $0.0076 | – | – |
| Structured extraction | 2,000 / 200 | $0.0003 | – | – |
More from Google
See also
Questions people ask
- What are Gemini 2.5 Flash Lite 09's benchmark scores?
- As of 25 Oct 2026, Gemini 2.5 Flash Lite 09 (thinking effort) scores 47.9 ±3.0 on the BenchLeader Index, strongest in long context (57) and weakest in reasoning (41). That rests on 15 independent benchmark results, and every score on this page links to its publisher.
- How does Gemini 2.5 Flash Lite 09 rank?
- Gemini 2.5 Flash Lite 09 (thinking effort) is #443 of 785 ranked configurations on 25 Oct 2026. 290 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- How much does Gemini 2.5 Flash Lite 09 cost per 1M tokens?
- As of 25 Oct 2026, Gemini 2.5 Flash Lite 09 costs $0.100 per 1M input tokens and $0.400 per 1M output tokens, $0.175 blended (three input tokens per output token).
- When was Gemini 2.5 Flash Lite 09 released?
- Google released Gemini 2.5 Flash Lite 09 on 25 Sept 2025. BenchLeader has results for it at 3 reasoning-effort settings.
Data as of 25 Oct 2026. Compare these configurations.
Cite as: BenchLeader, “Gemini 2.5 Flash Lite 09: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/gemini-2-5-flash-lite-09.