Skip to main content
BenchLM
Data

Data as of November 17, 2026 · How the score is built

Superseded.Google has newer models in this line:Gemini 3.6 Flash

Gemini 3.5 Flash

SupersededProprietaryReasoning

Decision readingGemini 3.5 Flash scores 61.9 out of 100 and ranks #44 of 216. This profile shows 39 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #15. API pricing is $1.5 input and $9 output per million tokens, with cached input at $0.15.

Email me when its price, rank or availability changes.

Capability

61.9/100

field median 49.4#44 of 216 ranked models

Public

#44of 216

Verified #28 of 80

Price

$1.50input / $9 output

input median $0.60cached $0.15 · batch + cache $0.075 · blended $5.25

Speed

188tok/s

field median 89.5 tok/sFirst token 12.96 s

Context

1Mtokens

field median 256,000Maximum output length is tracked separately

Decision snapshot

Where this model sits in the ranked field, its strongest published evidence, and what to validate before choosing it. The marker compares it with the current ranked catalog, not with an absolute quality threshold.

Strongest published evidence

Multimodal & Grounded ranks #15. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Validate before choosing

39 published rows leave some tracked benchmark slots empty. Agentic is its lowest eligible category at #57.

Source-linked · 39 displayable benchmark rows

Is Gemini 3.5 Flash right for your job?

Its place on the LLM Selector’s job rankings, the same order the job pages publish. Describe your own job to see where it stands for that.

Gemini 3.5 Flash has a newer version, Gemini 4 Hydrogen. Where Gemini 4 Hydrogen ranks by benchmark score:

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

Category score record

Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #57 of 138Percentile 59thWeight 22%9 benchmarksVerified
50.2
CodingRank #46 of 163Percentile 72ndWeight 20%7 benchmarksVerified
50.2
ReasoningRank #53 of 160Percentile 67thWeight 17%4 benchmarksVerified
52.4
MultimodalRank #15 of 67Percentile 79thWeight 12%6 benchmarksVerified
67.9
KnowledgeRank #27 of 181Percentile 86thWeight 12%4 benchmarksMixed sources
65.6
MultilingualWeight 7%0 benchmarksNot measured
Not measured
Inst. FollowingRank #39 of 157Percentile 76thWeight 5%Not listedUnlisted sources
87.7
MathRank Not rankedWeight 5%2 benchmarksVerified
62.6

39 of 922 tracked benchmark slots have displayable evidence · bars run 0–100

Coverage details

How much of this is verified

Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.

  1. Agentic9/9 verified
  2. Coding7/7 verified
  3. Reasoning4/4 verified
  4. Multimodal6/6 verified
  5. Knowledge3/4 verified
  6. MultilingualNot measured
  7. Inst. FollowingNot measured
  8. Math2/2 verified
Verified sourceProvisionalNot measured

Capability shape

Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.

Gemini 3.5 Flash category percentile values

  • Agentic59th percentile
  • Coding72nd percentile
  • Reasoning67th percentile
  • Multimodal79th percentile
  • Knowledge86th percentile
  • MultilingualNot eligible
  • Instruction following76th percentile
  • MathNot eligible

The dashed outline is median of 6 nearest peers.

Eligible category ranks

  1. Agentic#57/138
  2. Coding#46/163
  3. Reasoning#53/160
  4. Multimodal#15/67
  5. Knowledge#27/181
  6. MultilingualNot ranked
  7. Inst. Following#39/157
  8. MathNot ranked
Top decileTop quartileMid-fieldNot eligible

Benchmark ledger

Every result says who ran the test. For this model, Google ran 13 of 39. Coding opens by default. The tick marks the best source-verified result in the catalog; provisional leaders do not set the reference.

Overall rank
#44
of 216 on the leaderboard
Reported by Google
13
Shown with that label
Other publishers
1
Another publisher’s document or table
Run by a benchmark
20
The benchmark’s own run
Independent runs
5
An outside evaluator’s run
Coding7 rows
Coding benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
SWE-bench Pro55.1%

Best verified: Claude Fable 5.2 · 93%

Gap37.9 behindReported by GoogleCounts26% ref. weight
LiveCodeBench (Vals)LiveCodeBench, Vals AI run87.6%

Best verified: Claude Fable 5.1 · 90.5%

Gap2.9 behindIndependent run: Vals AICounts8% ref. weight
Terminal-Bench 2.176.2%

Best verified: SWE-2 · 92.8%

Gap16.6 behindReported by GoogleCountsScored in Agentic
Vibe Code BenchVibe Code Bench v1.148.68%

Best verified: Gemini 4 Argon · 91.90%

Gap43.2 behindRun by Vibe Code BenchShown only
cursorBench3149.8%

Best verified: Claude Fable 5 · 70.6%

Gap20.8 behindRun by cursorBench31Shown only
CursorBench 3.248.8%

Best verified: Claude Fable 5.1 · 73.4%

Gap24.6 behindRun by CursorBench 3.2Shown only
SWE-bench (Vals)SWE-bench, Vals AI run78.8%

Best verified: Claude Opus 5 · 97.0%

Gap18.2 behindIndependent run: Vals AIShown only
Agentic9 rows
Agentic benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Terminal-Bench 2.176.2%

Best verified: SWE-2 · 92.8%

Gap16.6 behindReported by GoogleCounts9% ref. weight
OSWorld-Verified78.4%

Best verified: Qwen3.8 Max · 86.1%

Gap7.7 behindReported by GoogleCounts8% ref. weight
MCP Atlas83.6%

Best verified: Muse Spark Open · 89.2%

Gap5.6 behindReported by GoogleCounts5% ref. weight
Terminal-Bench 2.1 (Vals)Terminal-Bench 2.1, Vals AI run74.2%

Best verified: Claude Opus 5.5 · 87.6%

Gap13.4 behindIndependent run: Vals AICounts4% ref. weight
Toolathlon56.5%

Best verified: Muse Spark 1.1 · 75.6%

Gap19.1 behindReported by GoogleCounts3% ref. weight
Finance Agent v257.9%

Best verified: Gemini 4 Argon · 65.4%

Gap7.5 behindRun by Finance Agent v2Shown only
Gert LabsGert Labs Composite Game Benchmark61.85%

Best verified: Claude Opus 4.8 · 72.97%

Gap11.1 behindRun by Gert LabsShown only
ResearchClawBench18.0%

Best verified: Claude Opus 4.8 · 21.1%

Gap3.1 behindRun by ResearchClawBenchShown only
MazeBenchMazeBench: visual spatial reasoning in a 3D open world0%

Best verified: GPT-6 Astra · 24%

Gap24 behindRun by MazeBenchShown only
Reasoning4 rows
Reasoning benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
MRCRv277.3%

Best verified: Sakana Fugu-Ultra · 93.6%

Gap16.3 behindReported by GoogleCounts20% ref. weight
ARC-AGI-2Abstraction and Reasoning Corpus for AGI v272.1%

Best verified: GPT-6 Astra · 95%

Gap22.9 behindReported by GoogleCounts15% ref. weight
MRCR 1M26.6%

Best verified: DeepSeek V4 Pro 0813 · 83.5%

Gap56.9 behindReported by GoogleShown only
ARC-AGI-1ARC-AGI-1 Semi-Private Evaluation92.50%

Best verified: Claude Fable 5 · 98.50%

Gap6 behindRun by ARC-AGI-1Shown only
Multimodal6 rows
Multimodal benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
MMMU-ProMassive Multi-discipline Multimodal Understanding Pro83.6%

Best verified: GPT-6.1 Terra · 85.5%

Gap1.9 behindReported by GoogleCounts28% ref. weight
CharXivCharXiv Reasoning84.2%

Best verified: Qwen3.8 Max · 93.5%

Gap9.3 behindReported by GoogleCounts16% ref. weight
ParseBench-1ParseBench-1: document parsing for AI agents (LlamaIndex leaderboard, first release)73.22%

Best verified: Claude Opus 5.5 · 78.80%

Gap5.6 behindRun by ParseBench-1Counts6% ref. weight
ParseBench-2ParseBench-2: severity-aware document parsing (LlamaIndex leaderboard)74.73%

Best verified: Claude Opus 5.5 · 85.75%

Gap11 behindRun by ParseBench-2Shown only
ExtractBench (LlamaIndex)ExtractBench: schema-guided enterprise document extraction (LlamaIndex leaderboard)79.84%

Best verified: GPT-6.1 Sol · 95.31%

Gap15.5 behindRun by ExtractBench (LlamaIndex)Shown only
Blueprint-Bench 233.6%

Best verified: Gemini 4 Carbon · 58.6%

Gap25 behindReported by GoogleShown only
Knowledge4 rows
Knowledge benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
HLEHumanity's Last Exam40.2%

Best verified: Claude Fable 5.2 · 74.2%

Gap34 behindReported by GoogleCounts44% ref. weight
MMLU-Pro (Vals)MMLU-Pro, Vals AI run89.5%

Best verified: Claude Fable 5.1 · 92.4%

Gap2.9 behindIndependent run: Vals AICounts6% ref. weight
GPQA Diamond (Vals)GPQA Diamond, Vals AI run92.7%

Best verified: Gemini 3.1 Pro · 95.5%

Gap2.8 behindIndependent run: Vals AICounts2% ref. weight
GPQA-DGPQA Diamond92.7%

Best verified: GPT-6 Astra · 96.0%

Gap3.3 behindReported by a third partyShown only
Math2 rows
Math benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-362.807%

Best verified: Claude Fable 5.2 · 95.088%

Gap32.3 behindRun by FrontierMath v2 (Tiers 1-3)CountsWeighted 30%
FrontierMath v2 (Tier 4)FrontierMath v2 Tier 426.829%

Best verified: Claude Fable 5.2 · 100.000%

Gap73.2 behindRun by FrontierMath v2 (Tier 4)CountsWeighted 10%
External signals7 rows
External signals benchmark results, best verified comparison, who ran each test, and whether it counts toward a rank
Game Arena Go756

Best verified: Claude Fable 5.2 · 1877

Gap1121 behindRun by Game Arena GoShown only
SkillsBench official leaderboard (BenchFlow)SkillsBench v1.1 official leaderboard (BenchFlow)48.2%

Best verified: GPT-5.5 · 67.3%

Gap19.1 behindRun by the benchmarkShown only
NYT ConnectionsNYT Connections LLM Benchmark (extended version)92.6%

Best verified: Gemini 4 Carbon · 99.3%

Gap6.7 behindRun by NYT ConnectionsShown only
BabaIsBenchBabaIsBench (Baba Is You intro levels, pass@1)88%

Best verified: Claude Opus 5 · 100%

Gap12 behindRun by BabaIsBenchShown only
Chess PuzzlesChess Puzzles (Epoch AI)45.0%

Best verified: Claude Fable 5.2 · 79.0%

Gap34 behindRun by Chess PuzzlesShown only
Mystery Game PuzzlesMystery Game Puzzles (Epoch AI)32.0%

Best verified: Claude Fable 5.2 · 90.0%

Gap58 behindRun by Mystery Game PuzzlesShown only
EBR-benchEarthborne Rangers (EBR-bench)4.8%

Best verified: Claude Fable 5.2 · 90.5%

Gap85.7 behindRun by EBR-benchShown only

Outlined bars are lab-reported. Filled bars are benchmark-run or independent.

What it costs to get this score

Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.

Current modelExplore all models

Gemini 3.5 Flash · 61.9 score · $5.25 blended per million tokens

The chart opens on the current model. Scroll horizontally to inspect the full price axis.

405060708090100$0.10$0.50$1$5$10$25$50$100↘ frontierGemini 3.5 Flash

Horizontal: blended price per million tokens, log scale · Vertical: public score

Lineage

The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.

  1. December 2025

    Gemini 3 Flash

    Score 53.8 · $0.5 / $3

  2. May 19, 2026 · you are here

    Gemini 3.5 Flash

    Score 61.9 · $1.5 / $9

  3. Jul 21, 2026

    Gemini 3.6 Flash

    Score 62.2 · $0.75 / $3.75

Spec sheet

Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.

API model ID
gemini-3.5-flashGoogle Gemini API pricing
Maximum output
Not sourced yet
Knowledge cutoff
Not sourced yet
Input modalities
text, image, video, audio, pdfGemini API model page for gemini-3.5-flash
Parameters
Not disclosed by the provider
Availability
Not sourced yet
Cloud regions
Not tracked yet
Lifecycle
Superseded
API capabilities
Tool calling, structured outputs, and batch support are not tracked yet
Prompt caching
Published at $0.15 per million cached input tokensGoogle Gemini API pricing
Self-host
Weights are not published
Rate limits
Not tracked yet

How to read this profile

The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.

Gemini 3.5 Flash ranks #44 of 216 on the public leaderboard with a score of 61.92/100. Its source-verified position is #28 of 80.

Gemini 3.5 Flash is a proprietary model with a 1M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.

Gemini 3.5 Flash sits in the Gemini 3.5 Flash family with Gemini 3.5 Flash Cyber. Its explicit predecessor is Gemini 3 Flash. 39 of 922 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.

Its strongest eligible category is Multimodal & Grounded at #15, while its lowest eligible position is Agentic at #57. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Last updated November 17, 2026. Runtime fields remain blank until a sourced snapshot exists.

Deployment options

Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.

Where to run Gemini 3.5 Flash by API

2 hosts publish a per-token price for it. DeepInfra has the lowest output rate, $9.00 per million tokens. Prices read from each host’s own pages on November 16, 2026.

Inference hosts for Gemini 3.5 Flash with input, output and cached-input prices per million tokens.
HostInput /1MOutput /1MCached /1MContext
DeepInfra$1.50$9.00—1M
OpenRouter$1.50$9.00$0.151.05M
Compare inference hosts

Questions

How does Gemini 3.5 Flash perform overall in AI benchmarks?

Gemini 3.5 Flash ranks #44 out of 216 models on the public BenchAlign leaderboard, with a score of 61.92/100. Its evidence status is Supported, and this profile shows 39 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.

Is Gemini 3.5 Flash good for knowledge and understanding?

Gemini 3.5 Flash ranks #27 out of 181 eligible models for knowledge and understanding, with a public category score of 65.6/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemini 3.5 Flash good for coding and programming?

Gemini 3.5 Flash ranks #46 out of 163 eligible models for coding and programming, with a public category score of 50.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemini 3.5 Flash good for mathematics?

Gemini 3.5 Flash has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.

Is Gemini 3.5 Flash good for reasoning and logic?

Gemini 3.5 Flash ranks #53 out of 160 eligible models for reasoning and logic, with a public category score of 52.4/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemini 3.5 Flash good for agentic tool use and computer tasks?

Gemini 3.5 Flash ranks #57 out of 138 eligible models for agentic tool use and computer tasks, with a public category score of 50.2/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Is Gemini 3.5 Flash good for multimodal and grounded tasks?

Gemini 3.5 Flash ranks #15 out of 67 eligible models for multimodal and grounded tasks, with a public category score of 67.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.

Which sibling models are related to Gemini 3.5 Flash?

Gemini 3.5 Flash belongs to the Gemini 3.5 Flash family. Related tracked variants include Gemini 3.5 Flash Cyber. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.

Does Gemini 3.5 Flash have full benchmark coverage on BenchLM?

No. Gemini 3.5 Flash currently has 63 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.

What is the context window size of Gemini 3.5 Flash?

Gemini 3.5 Flash has a documented context window of 1M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.

Compare Gemini 3.5 Flash with every tracked model1039 comparisons