Skip to main content

Model profile

Gemini 3 Flash

GoogleSupersededReleased December 2025
Data verified
Superseded:Google has released newer models in this line —Gemini 3.5 Flash
Overall Score
60.49Public #49 of 200Verified #38 of 99
Arena Elo
1473
Eligible category ranks
2of 8
Price (1M tokens)
$0.5 in / $3 out
API pricing
Speed
159tok/s
Context
1M

Evidence coverage

19 of 321 tracked benchmarks are published. 6 are verified and 13 provisional. 7 of 8 categories are measured.

Updated July 20, 2026Methodology
Published / tracked
19 / 321
Verified
6
Provisional
13
Categories with evidence
7 / 8

Evidence by category

  • Agentic4 benchmarks
    Mixed evidence
  • Coding2 benchmarks
    Mixed evidence
  • Reasoning2 benchmarks
    Reported
  • Knowledge6 benchmarks
    Reported
  • Math2 benchmarks
    Verified
  • Multilingual0 benchmarks
    Not measured
  • Multimodal2 benchmarks
    Reported
  • Inst. Following1 benchmark
    Reported
ProprietaryNon-Reasoning
Confidence:
Low
base

Gemini 3 Flash ranks #49 out of 200 models on the public leaderboard with an overall score of 60.49/100. It also ranks #38 out of 99 on the verified leaderboard. While not a frontier model, it offers specific advantages depending on the use case.

Gemini 3 Flash is a proprietary model with a 1M token context window. It processes queries without explicit chain-of-thought reasoning, offering faster response times and lower token usage.

This profile currently has 19 of 321 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Coding (#76), while its weakest is Agentic (#115). This performance profile makes it particularly well-suited for software development and code generation tasks.

Peer position

Exact provisional scores and ranks for the closest listed peers. A score can appear before a model clears the evidence threshold for a rank, so equal scores can have different rank states.

Range 60.4260.89

  1. GPT-5.4 Pro
    OpenAI
    #4460.89
    GPT-5.4 Pro is #44 with a score of 60.89.
    Compare
  2. Qwen3.5-27B
    Alibaba
    #4560.7
    Qwen3.5-27B is #45 with a score of 60.7.
    Compare
  3. DeepSeek V4 Pro
    DeepSeek
    #4660.66
    DeepSeek V4 Pro is #46 with a score of 60.66.
    Compare
  4. Qwen3.5-122B-A10B
    Alibaba
    #4760.56
    Qwen3.5-122B-A10B is #47 with a score of 60.56.
    Compare
  5. Grok 4.1 Fast (Reasoning)
    xAI
    #4860.51
    Grok 4.1 Fast (Reasoning) is #48 with a score of 60.51.
    Compare
  6. Gemini 3 FlashCurrent model
    Google
    #4960.49
    Gemini 3 Flash is #49 with a score of 60.49.
  7. Grok 4
    xAI
    #5060.42
    Grok 4 is #50 with a score of 60.42.
    Compare

Category percentile

More

Relative position among models eligible for each sourced category. A higher percentile means a stronger position within that category's ranked cohort; 100 is highest.

  1. Coding38%
    Eligible cohort rank #76 of 122Category score 48.2
  2. Agentic3%
    Eligible cohort rank #115 of 119Category score 25.2

Category evidence

Scores and ranks appear only where this model has published benchmark evidence. Categories without displayable source records remain not measured.

Category scores, ranks, weighting, benchmark coverage, and evidence status
CategoryScore
AgenticRank #115 of 119Percentile 3rdWeight 22%4 benchmarksMixed sources25.2
CodingRank #76 of 122Percentile 38thWeight 20%2 benchmarksMixed sources48.2
ReasoningRank Not rankedWeight 17%2 benchmarksReported75.4
KnowledgeRank Not rankedWeight 12%6 benchmarksReported41.2
MathRank Not rankedWeight 5%2 benchmarksVerified50.5
MultilingualWeight 7%0 benchmarksNot measuredNot measured
MultimodalRank Not rankedWeight 12%2 benchmarksReported79.8
Inst. FollowingRank Not rankedWeight 5%1 benchmarkReported77.5

Chatbot Arena performance

Scroll horizontally to inspect confidence intervals and vote counts.

Chatbot Arena Elo, confidence interval, and vote count by evaluation view
ViewEloConfidence intervalVotes
Text Overall1473±4.430,698
Coding1509±7.96,386
Math1476±13.21,992
Instruction Following1458±7.38,089
Creative Writing1458±9.44,681
Multi-turn1484±8.65,318
Hard Prompts1493±5.616,558
Hard Prompts (English)1488±7.37,854
Longer Query1476±7.47,873

Benchmark Details

Rows below have a displayable published verification record. Each source link and provenance note remains in the page HTML while its category is closed. Source-unverified manual rows and generated rows stay hidden.

Agentic4 benchmarks
Claw-EvalBenchmark exact
49.2%Display only
Source: Claw-Eval leaderboardProvenance: Claw-Eval reports this model as gemini3_flash in the official 2026-05-09 leaderboard snapshot. BenchLM stores the primary Pass^3 value on the local Claw-Eval display key.
τ²-bench resultsReported

τ²-Bench Tool-Agent-User Evaluation

43.3%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Gert LabsBenchmark exact

Gert Labs Composite Game Benchmark

56.63%Display only
Source: Gert Labs rankingsProvenance: Gert Labs reports this composite leaderboard score in the public rankings API. BenchLM scales the source gscore from 0-1 to 0-100 and stores it as a display-only agentic benchmark.
JobBenchBenchmark exact
11.4%Display only
Source: JobBench paperProvenance: JobBench reports Gemini-3-Flash under OpenCode on the main-set leaderboard. BenchLM stores the reported main-set score.
Coding2 benchmarks
Vibe Code BenchBenchmark exact

Vibe Code Bench v1.1

20.20%Display only
Source: Vals AI: Vibe Code Bench v1.1Provenance: Vals Vibe Code Bench v1.1 reports this exact row under google/gemini-3-flash-preview; BenchLM stores it on the local vibeCodeBench key.
AA-SciCodeReported

Artificial Analysis SciCode

49.9%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Reasoning2 benchmarks
AA-LCRReported

Artificial Analysis Long Context Reasoning

48.0%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
CritPtReported

Critical Physics Tasks

1.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Knowledge6 benchmarks
Artificial Analysis Intelligence IndexReported
27.4%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-GPQA DiamondReported

Artificial Analysis GPQA Diamond

81.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-HLEReported

Artificial Analysis Humanity's Last Exam

14.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience IndexReported

Artificial Analysis Omniscience Index

-3.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience AccuracyReported

Artificial Analysis Omniscience Accuracy

45.5%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
AA-Omniscience Hallucination RateReported

Artificial Analysis Omniscience Hallucination Rate

90.2%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Math2 benchmarks
FrontierMath v2 (Tiers 1-3)Benchmark exact

FrontierMath v2 Tiers 1-3

35.640%Weighted 30%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tiers 1-3 at 35.64% for gemini-3-flash-preview. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
FrontierMath v2 (Tier 4)Benchmark exact

FrontierMath v2 Tier 4

4.167%Weighted 10%
Source: Epoch AI FrontierMath v2 leaderboardProvenance: Epoch AI reports FrontierMath v2 Tier 4 at 4.167% for gemini-3-flash-preview. BenchLM selects the highest published thinking effort for the model and stores the v2 benchmark slice separately.
Multimodal2 benchmarks
AA-MMMU-ProReported

Artificial Analysis MMMU-Pro

78.6%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.
Design Arena WebsiteReported

Design Arena Website Elo

1228Display only
Source: OpenRouter model benchmarksProvenance: Display-only Design Arena Website Elo synced from OpenRouter model benchmark metadata. It is excluded from BenchLM weighted scoring.
Inst. Following1 benchmark
AA-IFBenchReported

Artificial Analysis IFBench

55.1%Display only
Source: Artificial Analysis model benchmarksProvenance: Display-only row synced from the current Artificial Analysis model payload. It is excluded from BenchLM weighted scoring.

Frequently Asked Questions

How does Gemini 3 Flash perform overall in AI benchmarks?

Gemini 3 Flash has 19 published benchmark scores on BenchLM, but it does not yet have enough non-generated coverage to receive a global overall rank.

Is Gemini 3 Flash good for knowledge and understanding?

Gemini 3 Flash has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Gemini 3 Flash good for coding and programming?

Gemini 3 Flash ranks #76 out of 122 models in coding and programming benchmarks with an average score of 48.2. There are stronger options in this category.

Is Gemini 3 Flash good for mathematics?

Gemini 3 Flash has visible benchmark coverage in mathematics, but BenchLM does not currently assign it a global category rank there.

Is Gemini 3 Flash good for reasoning and logic?

Gemini 3 Flash has visible benchmark coverage in reasoning and logic, but BenchLM does not currently assign it a global category rank there.

Is Gemini 3 Flash good for agentic tool use and computer tasks?

Gemini 3 Flash ranks #115 out of 119 models in agentic tool use and computer tasks benchmarks with an average score of 25.2. There are stronger options in this category.

Is Gemini 3 Flash good for multimodal and grounded tasks?

Gemini 3 Flash has visible benchmark coverage in multimodal and grounded tasks, but BenchLM does not currently assign it a global category rank there.

Is Gemini 3 Flash good for instruction following?

Gemini 3 Flash has visible benchmark coverage in instruction following, but BenchLM does not currently assign it a global category rank there.

Does Gemini 3 Flash have full benchmark coverage on BenchLM?

Not yet. Gemini 3 Flash currently has 19 published benchmark scores out of the 321 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Gemini 3 Flash?

Gemini 3 Flash has a published context window of 1M, which determines how much text it can process in a single interaction.

Last updated: July 20, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Choose with this week’s evidence

Join 2,000+ readers for ranking moves, new releases, pricing changes, and the evidence behind them.

Free. One email per week.