Skip to main content
BenchLM
Advertise

Model comparison

Gemini 3.5 Flash vs Gemini 3 Pro

Data verified

Head-to-head evidence from 19 shared benchmark results across 7 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.75/100
Margin
3.0pts
winning →
67.73/100
2 category wins0 category wins

Public leaderboard positions: Gemini 3.5 Flash #33 (Estimated); Gemini 3 Pro #19 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemini 3.5 Flash and Gemini 3 Pro share 19 comparable benchmark results. 3 of 8 categories are comparable. 27 results are unique to Gemini 3.5 Flash; 8 to Gemini 3 Pro.

Updated July 23, 2026
Shared results
19
Gemini 3.5 Flash only
27
Gemini 3 Pro only
8
Comparable categories
3 / 8

Pick Gemini 3 Pro if you want the stronger benchmark profile. Gemini 3.5 Flash only becomes the better choice if reasoning is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 19 shared benchmark results across 7 evidence categories; 3 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Gemini 3 Pro has the cleaner BenchAlign overall profile here, landing at 67.73 versus 64.75. It is a real lead, but still close enough that category-level strengths matter more than the headline number.

Gemini 3 Pro is also the more expensive model on tokens at $2.00 input / $12.00 output per 1M tokens, versus $1.50 input / $9.00 output per 1M tokens for Gemini 3.5 Flash. Gemini 3.5 Flash is the reasoning model in the pair, while Gemini 3 Pro is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Gemini 3 Pro gives you the larger context window at 2M, compared with 1M for Gemini 3.5 Flash.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Gemini 3.5 Flash and Gemini 3 Pro
CategoryGemini 3.5 FlashΔGemini 3 Pro
ReasoningGemini 3.5 Flash74.7Margin← 43.6Gemini 3 Pro31.1
MultimodalGemini 3.5 Flash83.8Margin← 2.7Gemini 3 Pro81.1
MathGemini 3.5 Flash32.9MarginTieGemini 3 Pro32.9
AgenticGemini 3.5 Flash77.2MarginNo overlapGemini 3 ProNot measured
CodingGemini 3.5 Flash53.9MarginNo overlapGemini 3 ProNot measured
KnowledgeGemini 3.5 Flash47.2MarginNo overlapGemini 3 ProNot measured
Inst. FollowingGemini 3.5 Flash76.3MarginNo overlapGemini 3 ProNot measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · Gemini 3.5 FlashB · Gemini 3 Pro

  1. ARC-AGI-2

    Reasoning
    Source ↗
    A 72.1%B 31.1%
    Winner: Gemini 3.5 FlashΔ 41
    ARC-AGI-2: Gemini 3.5 Flash scored 72.1%; Gemini 3 Pro scored 31.1%. Gemini 3.5 Flash wins this benchmark.

  2. FrontierMath v2 (Tier 4)

    Math
    Source ↗
    A 14.583%B 18.750%
    Winner: Gemini 3 ProΔ 4.2
    FrontierMath v2 (Tier 4): Gemini 3.5 Flash scored 14.583%; Gemini 3 Pro scored 18.750%. Gemini 3 Pro wins this benchmark.

  3. CharXiv

    Multimodal
    Source ↗
    A 84.2%B 81.4%
    Winner: Gemini 3.5 FlashΔ 2.8
    CharXiv: Gemini 3.5 Flash scored 84.2%; Gemini 3 Pro scored 81.4%. Gemini 3.5 Flash wins this benchmark.

  4. MMMU-Pro

    Multimodal
    Source ↗
    A 83.6%B 81%
    Winner: Gemini 3.5 FlashΔ 2.6
    MMMU-Pro: Gemini 3.5 Flash scored 83.6%; Gemini 3 Pro scored 81%. Gemini 3.5 Flash wins this benchmark.

  5. FrontierMath v2 (Tiers 1-3)

    Math
    Source ↗
    A 38.966%B 37.600%
    Winner: Gemini 3.5 FlashΔ 1.4
    FrontierMath v2 (Tiers 1-3): Gemini 3.5 Flash scored 38.966%; Gemini 3 Pro scored 37.600%. Gemini 3.5 Flash wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGemini 3.5 FlashGemini 3 ProComparison
Input / output priceUSD per 1M tokensGemini 3.5 Flash$1.5 input / $9 outputGemini 3 Pro$2 input / $12 outputGemini 3.5 Flash has the lower combined listed price.
Generation speedtokens per secondGemini 3.5 Flash284.2 tok/sGemini 3 Pro109 tok/sGemini 3.5 Flash has the higher measured throughput.
First-answer latencyseconds to first tokenGemini 3.5 Flash18.55 sGemini 3 Pro32.65 sGemini 3.5 Flash reaches the first token sooner.
Context windowmaximum listed tokensGemini 3.5 Flash1MGemini 3 Pro2MGemini 3 Pro lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemini 3.5 FlashGemini 3 ProResult
Terminal-Bench 2.0Source 76.2%—Not comparable
MCP AtlasSource 83.6%—Not comparable
ToolathlonSource 56.5%—Not comparable
OSWorld-VerifiedSource 78.4%—Not comparable
Finance Agent v2Source 57.9%—Not comparable
GDPval-AASource 1349—Not comparable
τ²-bench resultsSource 95.3%87.1%Gemini 3.5 Flash leads
GDPval-AASource 42.4%—Not comparable
AA Agentic IndexSource 37.5%—Not comparable
APEX-Agents-AASource 47.1%—Not comparable
Gert LabsSource 61.85%63.23%Gemini 3 Pro leads
ResearchClawBenchSource 18.0%—Not comparable
AA AutomationBenchSource 42.6%—Not comparable
AA EnterpriseOps-GymSource 50.1%—Not comparable
terminalBenchHardSource 40.9%—Not comparable
JobBenchSource —11.4%Not comparable
Coding
BenchmarkGemini 3.5 FlashGemini 3 ProResult
Terminal-Bench 2.0Source 76.2%—Not comparable
SWE-bench ProSource 55.1%—Not comparable
SciCodeSource 53.1%—Not comparable
Vibe Code BenchSource 48.68%14.30%Gemini 3.5 Flash leads
cursorBench31Source 49.8%—Not comparable
cursorBench32Source 48.8%—Not comparable
AA Coding IndexSource 70.1%—Not comparable
AA-SciCodeSource 53.1%56.1%Gemini 3 Pro leads
AA LiveCodeBenchSource —91.7%Not comparable
ReasoningGemini 3.5 Flash wins
BenchmarkGemini 3.5 FlashGemini 3 ProResult
MRCRv2Source 77.3%—Not comparable
MRCR 1MSource 26.6%—Not comparable
ARC-AGI-2Source 72.1%31.1%Gemini 3.5 Flash leads
AA-LCRSource 69.3%70.7%Gemini 3 Pro leads
CritPtSource 13.1%9.1%Gemini 3.5 Flash leads
Knowledge
BenchmarkGemini 3.5 FlashGemini 3 ProResult
Artificial Analysis Intelligence IndexSource 50.2%39.5%Gemini 3.5 Flash leads
GPQASource 92.2%—Not comparable
GPQA-DSource 92.7%—Not comparable
HLESource 40.2%—Not comparable
AA-Omniscience AccuracySource 51.9%55.9%Gemini 3 Pro leads
AA-Omniscience Hallucination RateSource 60.7%90.9%Gemini 3.5 Flash leads
AA-GPQA DiamondSource 92.2%90.8%Gemini 3.5 Flash leads
AA-HLESource 41.0%37.2%Gemini 3.5 Flash leads
AA-Omniscience IndexSource 22.7%15.8%Gemini 3.5 Flash leads
AA MMLU-ProSource —89.8%Not comparable
MathTie
BenchmarkGemini 3.5 FlashGemini 3 ProResult
FrontierMath v2 (Tiers 1-3)Source 38.966%37.600%Gemini 3.5 Flash leads
FrontierMath v2 (Tier 4)Source 14.583%18.750%Gemini 3 Pro leads
Multilingual
BenchmarkGemini 3.5 FlashGemini 3 ProResult
AA Global-MMLU-LiteSource —92.2%Not comparable
MultimodalGemini 3.5 Flash wins
BenchmarkGemini 3.5 FlashGemini 3 ProResult
CharXivSource 84.2%81.4%Gemini 3.5 Flash leads
MMMU-ProSource 83.6%81%Gemini 3.5 Flash leads
Blueprint-Bench 2Source 33.6%—Not comparable
AA-MMMU-ProSource 84.3%80.2%Gemini 3.5 Flash leads
Design Arena WebsiteSource 1285—Not comparable
MathVisionSource —86.6%Not comparable
VideoMMMUSource —87.6%Not comparable
ScreenSpot ProSource —72.7%Not comparable
V*Source —88.0%Not comparable
Inst. Following
BenchmarkGemini 3.5 FlashGemini 3 ProResult
IFBenchSource 76.3%—Not comparable
AA-IFBenchSource 76.3%70.4%Gemini 3.5 Flash leads
Frequently Asked Questions (4)

Which is better, Gemini 3.5 Flash or Gemini 3 Pro?

Gemini 3 Pro is ahead on BenchLM's BenchAlign leaderboard, 67.73 to 64.75. The biggest single separator in this matchup is ARC-AGI-2, where the scores are 72.1% and 31.1%.

Which is better for math, Gemini 3.5 Flash or Gemini 3 Pro?

Gemini 3.5 Flash and Gemini 3 Pro are effectively tied for math here, both landing at 32.9 on average.

Which is better for reasoning, Gemini 3.5 Flash or Gemini 3 Pro?

Gemini 3.5 Flash has the edge for reasoning in this comparison, averaging 74.7 versus 31.1. Inside this category, ARC-AGI-2 is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, Gemini 3.5 Flash or Gemini 3 Pro?

Gemini 3.5 Flash has the edge for multimodal and grounded tasks in this comparison, averaging 83.8 versus 81.1. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

Google Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.