Skip to main content
Radar

Five or fewer confirmed AI changes, with original sources, on mornings when something changed.A free source-linked morning brief.

Start free brief
BenchLM
Model A
Gemini 3.1 Pro

Google

56.0/100

Estimated · Public rank #93

90% interval 40.0–72.0

Gemini 3.1 Pro vs Gemini 3.5 Flash

Updated August 17, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Model B
Gemini 3.5 Flash

Google

64.7/100

Estimated · Public rank #39

90% interval 54.1–75.2

Decision reading

Gemini 3.5 Flash has the higher public score estimate, 64.67 versus 55.98, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

10 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Chat turn cost

    1K fresh input + 500 output tokens

    Gemini 3.5 Flash

    Gemini 3.5 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    Gemini 3.5 Flash

    Gemini 3.5 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    Gemini 3.5 Flash

    Gemini 3.5 Flash has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

Shared results
10
Gemini 3.1 Pro only
15
Gemini 3.5 Flash only
13
Like-for-like categories
2 / 8

1 category uses different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Math

Like-for-like
Gemini 3.1 Pro
31.8
Gemini 3.5 Flash
32.9
Weighted basis
2 vs 2 rows
Reading
Gemini 3.5 Flash leads

Multimodal

Like-for-like
Gemini 3.1 Pro
82.6
Gemini 3.5 Flash
83.8
Weighted basis
2 vs 2 rows
Reading
Gemini 3.5 Flash leads

Reasoning

Directional only
Gemini 3.1 Pro
77.1
Gemini 3.5 Flash
74.7
Weighted basis
1 vs 2 rows
Reading
Directional only

Agentic

Not comparable
Gemini 3.1 Pro
Not measured
Gemini 3.5 Flash
77.2
Weighted basis
0 vs 2 rows
Reading
Not comparable

Coding

Not comparable
Gemini 3.1 Pro
Not measured
Gemini 3.5 Flash
55.1
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
Gemini 3.1 Pro
Not measured
Gemini 3.5 Flash
40.2
Weighted basis
0 vs 1 rows
Reading
Not comparable

Multilingual

Not comparable
Gemini 3.1 Pro
Not measured
Gemini 3.5 Flash
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Gemini 3.1 Pro
Not measured
Gemini 3.5 Flash
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

Gemini 3.1 Pro
$0.008
Fits in one request
Gemini 3.5 Flash
$0.006
Fits in one request

Gemini 3.5 Flash has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Gemini 3.1 Pro
$0.136
Fits in one request
Gemini 3.5 Flash
$0.102
Fits in one request

Gemini 3.5 Flash has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

Gemini 3.1 Pro
$0.2
Fits in one request
Gemini 3.5 Flash
$0.15
Fits in one request

Gemini 3.5 Flash has the lower modeled cost

Costs use the listed standard API rates.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

Gemini 3.1 Pro

$0.2 per 1M cached input tokens

Google Gemini API pricing

Gemini 3.5 Flash

$0.15 per 1M cached input tokens

Google Gemini API pricing

Reasoning profile

Gemini 3.1 Pro

Reasoning

Gemini 3.5 Flash

Reasoning

Weight access

Gemini 3.1 Pro

Proprietary

Gemini 3.5 Flash

Proprietary

License

Gemini 3.1 Pro

Proprietary

Gemini 3.5 Flash

Proprietary

Release date

Gemini 3.1 Pro

2026-02-19

Gemini 3.5 Flash

2026-05-19

If you already use one of these models
Deployment change
Both entries list Google as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
Gemini 3.5 Flash has the higher public score estimate, 64.67 versus 55.98, but the 90% score intervals overlap.
Workload cost
Repository review: $0.136 vs $0.102. Cache-heavy agent loop: $0.2 vs $0.15.
Context tradeoff
Both models list 1M.

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence38 rows

Agentic

  • Claw-Eval

    Gemini 3.1 Pro57.8%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • DeepSearchQA

    Gemini 3.1 Pro69.7%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • τ²-bench results

    Gemini 3.1 Pro95.6%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • Gert Labs

    Shared source
    Gemini 3.1 Pro56.87%
    Gemini 3.5 Flash61.85%

    Gemini 3.5 Flash leads this result

  • ResearchClawBench

    Shared source
    Gemini 3.1 Pro13.3%
    Gemini 3.5 Flash18.0%

    Gemini 3.5 Flash leads this result

  • Terminal-Bench 2.0

    Gemini 3.1 Pro—
    Gemini 3.5 Flash76.2%
    Source

    Not directly comparable

  • MCP Atlas

    Gemini 3.1 Pro—
    Gemini 3.5 Flash83.6%
    Source

    Not directly comparable

  • Toolathlon

    Gemini 3.1 Pro—
    Gemini 3.5 Flash56.5%
    Source

    Not directly comparable

  • OSWorld-Verified

    Gemini 3.1 Pro—
    Gemini 3.5 Flash78.4%
    Source

    Not directly comparable

  • Finance Agent v2

    Gemini 3.1 Pro—
    Gemini 3.5 Flash57.9%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pro

    Gemini 3.1 Pro82.9%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • React Native Evals

    Gemini 3.1 Pro78.9%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • Vibe Code Bench

    Shared source
    Gemini 3.1 Pro32.03%
    Gemini 3.5 Flash48.68%

    Gemini 3.5 Flash leads this result

  • EEBench

    Shared source
    Gemini 3.1 Pro46.3%
    Gemini 3.5 Flash34.3%

    Gemini 3.1 Pro leads this result

  • CADGenBench Generation

    Gemini 3.1 Pro21.1%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • Terminal-Bench 2.0

    Gemini 3.1 Pro—
    Gemini 3.5 Flash76.2%
    Source

    Not directly comparable

  • SWE-bench Pro

    Gemini 3.1 Pro—
    Gemini 3.5 Flash55.1%
    Source

    Not directly comparable

  • cursorBench31

    Gemini 3.1 Pro—
    Gemini 3.5 Flash49.8%
    Source

    Not directly comparable

  • cursorBench32

    Gemini 3.1 Pro—
    Gemini 3.5 Flash48.8%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Gemini 3.1 Pro77.1%
    Source
    Gemini 3.5 Flash72.1%
    Source

    Gemini 3.1 Pro leads this result

  • ARC-AGI-3

    Gemini 3.1 Pro0.4%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • MRCRv2

    Gemini 3.1 Pro—
    Gemini 3.5 Flash77.3%
    Source

    Not directly comparable

  • MRCR 1M

    Gemini 3.1 Pro—
    Gemini 3.5 Flash26.6%
    Source

    Not directly comparable

Knowledge

  • GPQA-D

    Gemini 3.1 Pro94.3%
    Source
    Gemini 3.5 Flash92.7%
    Source

    Gemini 3.1 Pro leads this result

  • HLE w/o tools

    Gemini 3.1 Pro45.4%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • HealthBench Hard

    Gemini 3.1 Pro20.6%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • MedXpertQA (Text)

    Gemini 3.1 Pro71.5%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • HLE

    Gemini 3.1 Pro—
    Gemini 3.5 Flash40.2%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Gemini 3.1 Pro36.900%
    Gemini 3.5 Flash38.966%

    Gemini 3.5 Flash leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Gemini 3.1 Pro16.700%
    Gemini 3.5 Flash14.583%

    Gemini 3.1 Pro leads this result

Multimodal

  • MMMU-Pro

    Gemini 3.1 Pro83.9%
    Source
    Gemini 3.5 Flash83.6%
    Source

    Gemini 3.1 Pro leads this result

  • CharXiv

    Gemini 3.1 Pro80.2%
    Source
    Gemini 3.5 Flash84.2%
    Source

    Gemini 3.5 Flash leads this result

  • ERQA

    Gemini 3.1 Pro69.4%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • SimpleVQA

    Gemini 3.1 Pro72.4%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • ScreenSpot Pro

    Gemini 3.1 Pro84.4%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • ZeroBench

    Gemini 3.1 Pro29.0%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • MedXpertQA (MM)

    Gemini 3.1 Pro81.3%
    Source
    Gemini 3.5 Flash—

    Not directly comparable

  • Blueprint-Bench 2

    Gemini 3.1 Pro—
    Gemini 3.5 Flash33.6%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Gemini 3.1 Pro or Gemini 3.5 Flash?

Gemini 3.5 Flash has the higher public score estimate, 64.67 versus 55.98, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Gemini 3.1 Pro or Gemini 3.5 Flash?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, Gemini 3.1 Pro or Gemini 3.5 Flash?

The published evidence does not provide a shared weighted agentic tasks basis for both models, so BenchLM does not name a agentic tasks winner.

Which costs less, Gemini 3.1 Pro or Gemini 3.5 Flash?

For the stated presets, chat costs $0.008 on Gemini 3.1 Pro and $0.006 on Gemini 3.5 Flash; repository review costs $0.136 and $0.102; the cache-heavy agent loop costs $0.2 and $0.15. Costs use the listed standard API rates.

Which has the larger context window, Gemini 3.1 Pro or Gemini 3.5 Flash?

Both models list the same context window, 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 17, 2026

Watch Gemini 3.1 Pro vs Gemini 3.5 Flash

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.