Models / Gemini 2.5 Flash-Lite

Google

Gemini 2.5 Flash-Lite

Gemini 2.5 Flash-Lite is best for sticking to the facts; a strong pick at a modest price. The cheapest model of similar intelligence is Gemma 3 4B, at $0.04 per million tokens against $0.18.

Superseded. Gemini 3.5 Flash-Lite is Google's newer model in this line, at $0.85 blended: see Gemini 3.5 Flash-Lite.

Results 16 Nov 2026 · 32 results · 3 sources

Price per million tokens
$0.10 in · $0.40 out
Google's list price, 10 Nov 2026 · compare prices$0.01 cached input
Speed
Not measured
Intelligence Index
8.5
Artificial Analysis, at thinking reasoning; 6.7–8.5 across 2 settings
Spring Prompt overall
Not ranked yet
needs our benchmarks and two groups of results
Developer
Google, based in the US
Weights not published
Released
17 Jun 2025
1,048,576 tokens of context

Where it stands among the models you could choose

Available models grouped by price, intelligence, speed and developer location. Retired models are excluded.

AmongIntelligence IndexSpring Prompt overallPrice, blendedSpeed
Models available today 148th of 185Claude Opus 5.5 – $0.18 blended, 15th percentilecheapest: Mistral Nemo –
Models priced under $0.25 per million tokens 20th of 41Claude Haiku 5.5 – sets this group –
Models with similar intelligence sets this group – $0.18 blended, 35th percentilecheapest: Gemma 3 4B –
Models from developers based in the US 74th of 92Claude Opus 5.5 – $0.18 blended, 17th percentilecheapest: Gemma 3 4B –

The name under each rank is the leader of that group; green is the top quarter of the group and red the bottom quarter, by rank. Price is shown as a percentile: the share of the group that costs less, so lower is cheaper. "Sets this group" marks the measure the group is defined by. Spring Prompt overall is our score out of 100 across every source (how it works). Price is the developer's list price (or the typical OpenRouter host where we haven't read one) for three input tokens to one output; intelligence and speed are from Artificial Analysis (data sourced from Artificial Analysis); "similar intelligence" means within 4 points on its Intelligence Index. Developer locations are where each company is based, not where a model is served. Groups under 3 models are not ranked.

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced under $0.25 per million tokens. The bar shows its percentile in that field, best to the right. Open a row for the results behind it.

Product listingsTurning a sparse product feed and photos into listings that can go live Not measured
  • CatalogBench: has not measured this model.
Decks from an analysisTurning a finished analysis into a deck you could present as it is Not measured
  • DeckBench: has not measured this model.
User surveysPlanning a user survey and reading its results without being misled Not measured
  • SurveyBench: has not measured this model.
Marketing planningPlanning a year of ad spend without overspending Not measured
  • ROASBench: has not measured this model.
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 89th of 159 available · 9th of 37 at its price
BenchmarkGemini 2.5 Flash-LiteRank among availableBest available
Berkeley Function Calling Leaderboard (BFCL) V4BFCL: overall accuracy · reported 36.9% 21st of 36 Claude Opus 4.5 77.5%
  • tau2-bench: has not measured this model.
  • OpenHands Index: has not measured this model.
  • Microsoft STATE-Bench: has not measured this model.
  • Artificial Analysis: has not measured this model.
  • Vending-Bench 2: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects Not measured
  • APEX-Agents: has not measured this model.
  • GDP.pdf: has not measured this model.
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 147th of 187 available · 19th of 41 at its price
BenchmarkGemini 2.5 Flash-LiteRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 8.5 148th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 6.8% 139th of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 62.5% 129th of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality Not measured
  • Arena (formerly LMArena): has not measured this model.
  • UGI Leaderboard: has not measured this model.
Sticking to the factsSummarising without inventing things, and factual answers 2nd of 139 available · 1st of 30 at its price
BenchmarkGemini 2.5 Flash-LiteRank among availableBest available
Vectara Hallucination LeaderboardVectara: hallucination rate · reported 3.3% 2nd of 71 GPT-5.4 nano 3.1%
  • Arena (formerly LMArena): has not measured this model.
  • SimpleQA Verified (Epoch AI): has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) Not measured
  • BulletBench: has not measured this model.

Nearest alternatives

Against Gemini 2.5 Flash-Lite at $0.18 blended, Intelligence Index 8.5. "Similar intelligence" means within 4 points or better.

Where to run it

1 host on OpenRouter at the standard service tier, with a median of $0.17 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Google AI Studionot stated$0.10$0.40$0.18

Other service tiers, not counted above: Google AI Studio flex $0.05 in, $0.20 out; Google AI Studio priority $0.18 in, $0.72 out. Flex and batch are cheaper but slower or queued; priority and fast cost more.

Prices per million tokens from OpenRouter's public endpoint list, checked 10 Nov 2026.

Against the alternatives

The models you would most likely weigh it against: the leaders of the groups above.

Scroll sideways to see every alternative.

Gemini 2.5 Flash-LiteClaude Haiku 5.5
most intelligent at under $0.25 per million tokens
Gemma 3 4B
cheapest with similar intelligence
Claude Opus 5.5
most intelligent available today
Price per million tokens $0.18 $0.20$0.04$8.00
Tokens a second – 240–96
Intelligence Index 8.5 43.44.857.6
Spring Prompt overall – 40–82
Rank among available models, by use case
Product listings – 20th–13th
Decks from an analysis – 18th–7th
User surveys – 7th–4th
Marketing planning – 30th–9th
Agents and tool use 89th of 159 28th158th3rd
Professional work – ––3rd
Reasoning and knowledge 147th of 187 25th181st1st
Writing – –157th5th
Sticking to the facts 2nd of 139 –32nd3rd
Speed under pressure – 21st––

Shaded figures are better than Gemini 2.5 Flash-Lite's. A dash means no result.

Where it has been measured

20th most intelligent of the 41 models priced under $0.25 per million tokens. Among models available today, in the top quarter (by percentile) for sticking to the facts; in the bottom quarter for reasoning and knowledge.

Artificial Analysis lists it but has not published a speed for it yet

Every result

32 published results from 3 sources, each in the source's own units, with the configuration that produced it.

Artificial Analysis · reported by Artificial Analysis · 14 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 6.7 381 of 413 Gemini 2.5 Flash-Lite (no reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 8.5 346 of 413 Gemini 2.5 Flash-Lite (thinking reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 47.4% 327 of 360 Gemini 2.5 Flash-Lite (no reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 62.5% 285 of 360 Gemini 2.5 Flash-Lite (thinking reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 3.7% 399 of 419 Gemini 2.5 Flash-Lite (no reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 6.8% 317 of 419 Gemini 2.5 Flash-Lite (thinking reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 31.5% 261 of 288 Gemini 2.5 Flash-Lite (no reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 49.9% 141 of 288 Gemini 2.5 Flash-Lite (thinking reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 32.0% 336 of 407 Gemini 2.5 Flash-Lite (no reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 55.7% 260 of 407 Gemini 2.5 Flash-Lite (thinking reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 2.3% 260 of 282 Gemini 2.5 Flash-Lite (no reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 4.5% 237 of 282 Gemini 2.5 Flash-Lite (thinking reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 19.0% 259 of 286 Gemini 2.5 Flash-Lite (no reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 18.4% 261 of 286 Gemini 2.5 Flash-Lite (thinking reasoning) 20 Oct 2026

Not shown: Not business work, and a blend: read the parts for any one task.

Berkeley Function Calling Leaderboard (BFCL) V4 · reported by Berkeley Function Calling Leaderboard (BFCL) V4 · 16 results
MeasureValueRankConfigurationDated
BFCL: irrelevance detection% correct, higher is better 92.5% 9 of 109 Gemini 2.5 Flash-Lite (bfcl fc) 16 Dec 2025
BFCL: irrelevance detection% correct, higher is better 93.3% 7 of 109 Gemini 2.5 Flash-Lite (bfcl prompt) 16 Dec 2025
BFCL: memory% correct, higher is better 20.7% 43 of 109 Gemini 2.5 Flash-Lite (bfcl fc) 16 Dec 2025
BFCL: memory% correct, higher is better 12.7% 65 of 109 Gemini 2.5 Flash-Lite (bfcl prompt) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 13.5% 62 of 109 Gemini 2.5 Flash-Lite (bfcl fc) 16 Dec 2025
BFCL: multi-turn tasks% correct, higher is better 7.6% 75 of 109 Gemini 2.5 Flash-Lite (bfcl prompt) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 36.9% 52 of 109 Gemini 2.5 Flash-Lite (bfcl fc) 16 Dec 2025
BFCL: overall accuracy% correct, higher is better 28.0% 73 of 109 Gemini 2.5 Flash-Lite (bfcl prompt) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 43.8% 101 of 109 Gemini 2.5 Flash-Lite (bfcl fc) 16 Dec 2025
BFCL: relevance detection% correct, higher is better 50.0% 98 of 109 Gemini 2.5 Flash-Lite (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 86.6% 32 of 109 Gemini 2.5 Flash-Lite (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (curated)% correct, higher is better 83.9% 52 of 109 Gemini 2.5 Flash-Lite (bfcl prompt) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 65.8% 79 of 109 Gemini 2.5 Flash-Lite (bfcl fc) 16 Dec 2025
BFCL: single-turn calls (user-contributed)% correct, higher is better 54.9% 94 of 109 Gemini 2.5 Flash-Lite (bfcl prompt) 16 Dec 2025
BFCL: web search% correct, higher is better 21.0% 43 of 109 Gemini 2.5 Flash-Lite (bfcl fc) 16 Dec 2025
BFCL: web search% correct, higher is better 0.0% 92 of 109 Gemini 2.5 Flash-Lite (bfcl prompt) 16 Dec 2025

Not shown: Not general refusal or safety behaviour.

Vectara Hallucination Leaderboard · reported by Vectara Hallucination Leaderboard · 2 results
MeasureValueRankConfigurationDated
Vectara: answer rate% of documents, higher is better 99.5% 53 of 108 Gemini 2.5 Flash-Lite 22 Sep 2026
Vectara: hallucination rate% of summaries, lower is better 3.3% 3 of 108 Gemini 2.5 Flash-Lite 22 Sep 2026

Not shown: Not a quality score: a low rate usually means content filters were triggered, and hallucination rates are measured on answered documents only.

Test your own prompt.

Benchmarks aren't your task. Run your prompt on the models you could use, with every answer checked and costed.