Models / Gemini 3.5 Flash

Google

Gemini 3.5 Flash

Gemini 3.5 Flash is best for writing and speed under pressure; pick it when quality matters more than cost. The cheapest model of similar intelligence is MiMo-V2.6-Flash, at $0.18 per million tokens against $3.38.

Superseded. Gemini 3.8 Flash is Google's newer model in this line, at $3.00 blended: see Gemini 3.8 Flash or compare the two.

Results 16 Nov 2026 · 75 results · 9 sources

Test Gemini 3.5 Flash on your prompt → It runs beside the models you could use instead, with every answer checked and costed.

Price per million tokens
$1.50 in · $9.00 out
Google's list price, 10 Nov 2026 · compare prices$0.15 cached input
Speed
Not measured
Intelligence Index
33.6
Artificial Analysis, at medium reasoning; 23.8–33.6 across 3 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
19 May 2026
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 47th of 185Claude Opus 5.5 – $3.38 blended, 79th percentilecheapest: Mistral Nemo –
Models priced $3–10 per million tokens 20th of 38Claude Opus 5.5 – sets this group –
Models with similar intelligence sets this group – $3.38 blended, 67th percentilecheapest: DeepSeek-V4-Flash (0731) –
Models from developers based in the US 31st of 92Claude Opus 5.5 – $3.38 blended, 60th 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.

Measured cost per task

API cost recorded in our benchmark runs, excluding judging.

TaskBenchmarkCost per task
Game of bullet chessBulletBench≈ $0.029

How good is it, and for what?

Each use case ranks the available models its benchmarks measured, then those priced $3–10 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 49th of 159 available · 21st of 35 at its price
BenchmarkGemini 3.5 FlashRank among availableBest available
OpenHands IndexOpenHands Index: average · reported 62.6% 7th of 31 Claude Fable 5 81.0%
Artificial AnalysisArtificial Analysis: Terminal-Bench 4.0 · reported 6.6% 45th of 107 Kimi K3.1 Pro 67.2%
Artificial AnalysisArtificial Analysis: Terminal-Bench 2.1 · reported 78.7% 24th of 107 Claude Fable 5.1 91.4%
Artificial AnalysisArtificial Analysis: τ-bench banking · reported 32.2% 29th of 104 Grok 4.6 50.7%
Vending-Bench 2Vending-Bench 2: money after a year · reported $5,396 22nd of 53 GPT-6 Astra $15,515
  • tau2-bench: has not measured this model.
  • Berkeley Function Calling Leaderboard (BFCL) V4: pending. Its latest results are dated 16 Dec 2025, before this model was released.
  • Microsoft STATE-Bench: has not measured this model.
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 42nd of 51 available · 21st of 23 at its price
BenchmarkGemini 3.5 FlashRank among availableBest available
APEX-AgentsAPEX-Agents: tasks passed · reported 27.5% 35th of 37 Claude Sonnet 5.5 75.5%
GDP.pdfGDP.pdf: professional document tasks · reported 14.0% 24th of 31 GPT-5.6 Sol 30.7%
  • Remote Labor Index: has not measured this model.
Reasoning and knowledgeHard questions across science, maths and general knowledge 38th of 187 available · 21st of 39 at its price
BenchmarkGemini 3.5 FlashRank among availableBest available
Artificial AnalysisArtificial Analysis: Artificial Analysis Intelligence Index · reported 33.6 47th of 185 Claude Opus 5.5 57.6
Artificial AnalysisArtificial Analysis: Humanity's Last Exam · reported 42.7% 33rd of 186 Claude Opus 5.5 61.4%
Artificial AnalysisArtificial Analysis: GPQA Diamond · reported 92.2% 21st of 168 GPT-6 Astra 96.3%
WritingWhat people prefer in blind comparisons, and judged writing quality 13th of 169 available · 7th of 34 at its price
BenchmarkGemini 3.5 FlashRank among availableBest available
Arena (formerly LMArena)Arena Text: overall · reported 1,477 23rd of 153 Gemini 4 Argon 1,525
UGI LeaderboardUGI: writing score · reported 72.5 4th of 124 Gemini 3.8 Flash 78.6
Sticking to the factsSummarising without inventing things, and factual answers 16th of 139 available · 5th of 31 at its price
BenchmarkGemini 3.5 FlashRank among availableBest available
Arena (formerly LMArena)Arena Text factuality: overall · reported 1,476 15th of 109 Gemini 4 Argon 1,511
SimpleQA Verified (Epoch AI)SimpleQA Verified: correct answers · reported 66.2% 11th of 68 GPT-6 Astra 75.6%
  • Vectara Hallucination Leaderboard: has not measured this model.
Speed under pressureGood decisions against a real clock (fast chess) 4th of 35 available · 2nd of 14 at its price
BenchmarkGemini 3.5 FlashRank among availableBest available
BulletBenchBulletBench Lightning 10+1: ladder Elo 727 3rd of 18 Gemini 3.5 Flash-Lite 892
BulletBenchBulletBench Bullet 60s: ladder Elo 810 5th of 33 Gemini 3.8 Flash 1,068

Nearest alternatives

Against Gemini 3.5 Flash at $3.38 blended, Intelligence Index 33.6. "Similar intelligence" means within 4 points or better.

Where to run it

3 hosts on OpenRouter at the standard service tier, with a median of $3.38 blended per million tokens. Cheapest first.

HostQuantisationInputOutputBlended
Googlenot stated$1.50$9.00$3.38
Google AI Studionot stated$1.50$9.00$3.38
Googlenot stated$1.65$9.90$3.71

Other service tiers, not counted above: Google flex $0.75 in, $4.50 out; Google AI Studio flex $0.75 in, $4.50 out; Google priority $2.70 in, $16.20 out; Google AI Studio priority $2.70 in, $16.20 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 3.5 FlashClaude Opus 5.5
most intelligent at $3–10 per million tokens
DeepSeek-V4-Flash (0731)
cheapest with similar intelligence
Claude Fable 5.2
leads overall
Gemini 4 Argon
Google's best other model
Price per million tokens $3.38 $8.00$0.20$16.00$4.00
Tokens a second – 96–––
Intelligence Index 33.6 57.634.3–52.6
Spring Prompt overall – 82–9072
Rank among available models, by use case
Product listings – 13th–5th11th
Decks from an analysis – 7th–4th23rd
User surveys – 4th–1st15th
Marketing planning – 9th–1st13th
Agents and tool use 49th of 159 3rd43rd–5th
Professional work 42nd of 51 3rd–––
Reasoning and knowledge 38th of 187 1st47th–4th
Writing 13th of 169 5th––1st
Sticking to the facts 16th of 139 3rd105th–1st
Speed under pressure 4th of 35 ––8th26th

Shaded figures are better than Gemini 3.5 Flash's. A dash means no result.

Research and examples

Where it has been measured

20th most intelligent of the 38 models priced $3–10 per million tokens. Among models available today, in the top quarter (by percentile) for 4 of the 6 use cases measured, led by writing and speed under pressure; in the bottom quarter for professional work.

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

Every result

75 published results from 9 sources, each in the source's own units, with the configuration that produced it.

BulletBench · measured by Spring Prompt · 10 results
MeasureValueRankConfigurationDated
BulletBench Bullet 60s: cost per gameUS dollars, lower is better $0.0289 57 of 71 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Bullet 60s: games lost on time% of games, lower is better 25.0% 32 of 71 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Bullet 60s: invalid moves% of moves, lower is better 0.5% 67 of 71 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Bullet 60s: ladder Eloladder Elo, higher is better 810
582–1,006
6 of 71 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Bullet 60s: median move timemilliseconds, lower is better 1.2 s 36 of 71 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Lightning 10+1: cost per gameUS dollars, lower is better $0.0213 42 of 48 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Lightning 10+1: games lost on time% of games, lower is better 33.3% 35 of 48 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Lightning 10+1: invalid moves% of moves, lower is better 0.6% 43 of 48 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Lightning 10+1: ladder Eloladder Elo, higher is better 727
567–890
4 of 48 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026
BulletBench Lightning 10+1: median move timemilliseconds, lower is better 1.2 s 39 of 48 Gemini 3.5 Flash (minimal reasoning)
minimal reasoning
1 Oct 2026

Not shown: Not your cost: prices are those charged on the run date.

APEX-Agents · reported by APEX-Agents · 1 result
MeasureValueRankConfigurationDated
APEX-Agents: tasks passed% of tasks, higher is better 27.5% 37 of 39 Gemini 3.5 Flash 1 Oct 2026

Not shown: Not your firm's documents or tools; graded by rubric, not by a client.

Arena (formerly LMArena) · reported by Arena (formerly LMArena) · 16 results
MeasureValueRankConfigurationDated
Arena Document: overallArena rating, higher is better 1,453
1,444–1,463
29 of 44 Gemini 3.5 Flash (high reasoning) 13 Sep 2026
Arena Document: overallArena rating, higher is better 1,461
1,453–1,468
25 of 44 Gemini 3.5 Flash (medium reasoning) 13 Sep 2026
Arena Text factuality: overallArena rating, higher is better 1,476
1,473–1,480
20 of 182 Gemini 3.5 Flash (high reasoning) 2 Oct 2026
Arena Text factuality: overallArena rating, higher is better 1,467
1,463–1,470
35 of 182 Gemini 3.5 Flash (medium reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,468
1,461–1,475
41 of 406 Gemini 3.5 Flash (high reasoning) 2 Oct 2026
Arena Text: business, management and financeArena rating, higher is better 1,462
1,455–1,469
56 of 406 Gemini 3.5 Flash (medium reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,464
1,457–1,471
22 of 411 Gemini 3.5 Flash (high reasoning) 2 Oct 2026
Arena Text: creative writingArena rating, higher is better 1,469
1,461–1,476
18 of 411 Gemini 3.5 Flash (medium reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,492
1,484–1,501
55 of 363 Gemini 3.5 Flash (high reasoning) 2 Oct 2026
Arena Text: expert promptsArena rating, higher is better 1,487
1,479–1,496
63 of 363 Gemini 3.5 Flash (medium reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,465
1,459–1,471
43 of 413 Gemini 3.5 Flash (high reasoning) 2 Oct 2026
Arena Text: instruction followingArena rating, higher is better 1,466
1,460–1,471
41 of 413 Gemini 3.5 Flash (medium reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,477
1,473–1,481
28 of 413 Gemini 3.5 Flash (high reasoning) 2 Oct 2026
Arena Text: overallArena rating, higher is better 1,476
1,472–1,480
31 of 413 Gemini 3.5 Flash (medium reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,474
1,467–1,480
18 of 412 Gemini 3.5 Flash (high reasoning) 2 Oct 2026
Arena Text: writing, literature and languageArena rating, higher is better 1,472
1,465–1,478
22 of 412 Gemini 3.5 Flash (medium reasoning) 2 Oct 2026

Not shown: Not accuracy or correctness: it ranks which answer voters preferred, with answer length and formatting controlled for.

Artificial Analysis · reported by Artificial Analysis · 26 results
MeasureValueRankConfigurationDated
Artificial Analysis: Artificial Analysis Coding Indexindex score, higher is better 70.1 52 of 187 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 32.6 104 of 413 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 33.6 100 of 413 Gemini 3.5 Flash (medium reasoning) 20 Oct 2026
Artificial Analysis: Artificial Analysis Intelligence Indexindex score, higher is better 23.8 168 of 413 Gemini 3.5 Flash (minimal reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 92.2% 39 of 360 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 92.1% 40 of 360 Gemini 3.5 Flash (medium reasoning) 20 Oct 2026
Artificial Analysis: GPQA Diamond% of questions, higher is better 82.8% 151 of 360 Gemini 3.5 Flash (minimal reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 42.7% 65 of 419 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 41.3% 78 of 419 Gemini 3.5 Flash (medium reasoning) 20 Oct 2026
Artificial Analysis: Humanity's Last Exam% of questions, higher is better 24.1% 182 of 419 Gemini 3.5 Flash (minimal reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 76.3% 18 of 288 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 74.6% 32 of 288 Gemini 3.5 Flash (medium reasoning) 20 Oct 2026
Artificial Analysis: IFBench% of instructions, higher is better 47.3% 154 of 288 Gemini 3.5 Flash (minimal reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 73.3% 171 of 407 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 74.3% 157 of 407 Gemini 3.5 Flash (medium reasoning) 20 Oct 2026
Artificial Analysis: Long-context reasoning (AA-LCR)% of questions, higher is better 61.3% 248 of 407 Gemini 3.5 Flash (minimal reasoning) 20 Oct 2026
Artificial Analysis: SciCode% of problems, higher is better 53.9% 71 of 205 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 2.1% of tasks, higher is better 78.7% 50 of 188 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench 4.0% of tasks, higher is better 6.6% 106 of 204 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 40.9% 51 of 282 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 39.4% 55 of 282 Gemini 3.5 Flash (medium reasoning) 20 Oct 2026
Artificial Analysis: Terminal-Bench Hard% of tasks, higher is better 46.2% 29 of 282 Gemini 3.5 Flash (minimal reasoning) 20 Oct 2026
Artificial Analysis: τ-bench banking% of tasks, higher is better 32.2% 54 of 175 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 95.3% 22 of 286 Gemini 3.5 Flash (high reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 95.6% 18 of 286 Gemini 3.5 Flash (medium reasoning) 20 Oct 2026
Artificial Analysis: τ²-bench telecom% of tasks, higher is better 58.8% 153 of 286 Gemini 3.5 Flash (minimal reasoning) 20 Oct 2026

Not shown: Not your codebase or tools.

GDP.pdf · reported by GDP.pdf · 2 results
MeasureValueRankConfigurationDated
GDP.pdf: professional document tasks% of rubric, higher is better 14.0% 35 of 49 Gemini 3.5 Flash 6 Jun 2026
GDP.pdf: professional document tasks% of rubric, higher is better 14.0% 35 of 49 Gemini 3.5 Flash (medium reasoning) 1 Oct 2026

Not shown: Not your documents; 100 tasks, so small differences are noise.

OpenHands Index · reported by OpenHands Index · 6 results
MeasureValueRankConfigurationDated
OpenHands Index: average% resolved, higher is better 62.6% 7 of 34 Gemini 3.5 Flash (openhands) 30 Jun 2026
OpenHands Index: front end (SWE-Bench Multimodal)% resolved, higher is better 39.7% 9 of 34 Gemini 3.5 Flash (openhands) 30 Jun 2026
OpenHands Index: greenfield (Commit0)% resolved, higher is better 37.5% 10 of 34 Gemini 3.5 Flash (openhands) 30 Jun 2026
OpenHands Index: information gathering (GAIA)% resolved, higher is better 81.2% 5 of 34 Gemini 3.5 Flash (openhands) 30 Jun 2026
OpenHands Index: issue resolution (SWE-Bench)% resolved, higher is better 78.6% 4 of 34 Gemini 3.5 Flash (openhands) 30 Jun 2026
OpenHands Index: testing (SWT-Bench)% resolved, higher is better 76.2% 8 of 34 Gemini 3.5 Flash (openhands) 30 Jun 2026

Not shown: Not the model alone: the score is for the model inside the OpenHands agent, at the SDK version shown.

SimpleQA Verified (Epoch AI) · reported by SimpleQA Verified (Epoch AI) · 1 result
MeasureValueRankConfigurationDated
SimpleQA Verified: correct answers% of questions, higher is better 66.2% 11 of 85 Gemini 3.5 Flash (high reasoning) 27 Aug 2026

Not shown: Not answers grounded in your documents; tests what the model remembers.

UGI Leaderboard · reported by UGI Leaderboard · 12 results
MeasureValueRankConfigurationDated
UGI: requested-length error% off the requested word count, lower is better 14.0% 119 of 379 Gemini 3.5 Flash (high reasoning) 21 May 2026
UGI: requested-length error% off the requested word count, lower is better 9.0% 75 of 379 Gemini 3.5 Flash (low reasoning) 21 May 2026
UGI: requested-length error% off the requested word count, lower is better 12.0% 106 of 379 Gemini 3.5 Flash (medium reasoning) 21 May 2026
UGI: requested-length error% off the requested word count, lower is better 13.0% 111 of 379 Gemini 3.5 Flash (minimal reasoning) 21 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.34 233 of 379 Gemini 3.5 Flash (high reasoning) 21 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.35 210 of 379 Gemini 3.5 Flash (low reasoning) 21 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.35 182 of 379 Gemini 3.5 Flash (medium reasoning) 21 May 2026
UGI: style adherencescore from 0 to 1, higher is better 0.33 268 of 379 Gemini 3.5 Flash (minimal reasoning) 21 May 2026
UGI: writing scorescore out of 100, higher is better 69.7 26 of 379 Gemini 3.5 Flash (high reasoning) 21 May 2026
UGI: writing scorescore out of 100, higher is better 72.4 11 of 379 Gemini 3.5 Flash (low reasoning) 21 May 2026
UGI: writing scorescore out of 100, higher is better 72.5 9 of 379 Gemini 3.5 Flash (medium reasoning) 21 May 2026
UGI: writing scorescore out of 100, higher is better 72.5 10 of 379 Gemini 3.5 Flash (minimal reasoning) 21 May 2026

Not shown: Not other format limits such as character counts or bullet counts.

Vending-Bench 2 · reported by Vending-Bench 2 · 1 result
MeasureValueRankConfigurationDated
Vending-Bench 2: money after a yearUS dollars, higher is better $5,396 23 of 63 Gemini 3.5 Flash 1 Oct 2026

Not shown: Not a real business; one simulated market with set rules.

Embed a score badge

A badge for each of our benchmarks that ranked Gemini 3.5 Flash, from the current results. Paste the code into a page or README; it links back to the benchmark.

Gemini 3.5 Flash is #4 of 45 on BulletBench (Lightning 10+1: 727), measured by Spring Prompt BulletBench · Lightning 10+1
<a href="https://springprompt.com/benchmarks/bulletbench?focus=google-gemini-3-5-flash"><img src="https://springprompt.com/badge/bulletbench/google-gemini-3-5-flash.svg" alt="Gemini 3.5 Flash is #4 of 45 on BulletBench (Lightning 10+1: 727), measured by Spring Prompt" height="20"></a>

Will Gemini 3.5 Flash work for your product?

Benchmarks aren't your task. Paste the prompt your product uses and run it beside the models you could use instead, with every answer checked and costed.

New here? Your email starts a free trial. No credit card needed.