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.

See the free Radar Brief
BenchLM
Google logo
Model A
Gemini 3.1 Pro

Google

56.49/100

Estimated · Public rank #103

90% interval 40.4–72.6

Gemini 3.1 Pro vs GPT-5.4

Updated September 3, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

OpenAI logo
Model B
GPT-5.4

OpenAI

72.89/100

Supported · Public rank #20

90% interval 69.1–76.7

Decision reading

GPT-5.4 has the higher public score estimate, 72.89 versus 56.49, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

23 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.

  • Long documents

    Prompts that approach the documented context limit

    GPT-5.4

    GPT-5.4 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    Gemini 3.1 Pro

    Gemini 3.1 Pro 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 3.1 Pro

    Gemini 3.1 Pro 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 3.1 Pro

    Gemini 3.1 Pro 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

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
23
Gemini 3.1 Pro only
0
GPT-5.4 only
14
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.

Reasoning

Like-for-like
Gemini 3.1 Pro
77.1
GPT-5.4
74.0
Weighted basis
1 vs 1 rows
Reading
Gemini 3.1 Pro leads

Math

Like-for-like
Gemini 3.1 Pro
31.8
GPT-5.4
42.5
Weighted basis
2 vs 2 rows
Reading
GPT-5.4 leads

Multimodal

Directional only
Gemini 3.1 Pro
82.6
GPT-5.4
73.2
Weighted basis
2 vs 3 rows
Reading
Directional only

Agentic

Not comparable
Gemini 3.1 Pro
Not measured
GPT-5.4
77.2
Weighted basis
0 vs 3 rows
Reading
Not comparable

Coding

Not comparable
Gemini 3.1 Pro
Not measured
GPT-5.4
57.7
Weighted basis
0 vs 1 rows
Reading
Not comparable

Knowledge

Not comparable
Gemini 3.1 Pro
Not measured
GPT-5.4
57.6
Weighted basis
0 vs 2 rows
Reading
Not comparable

Multilingual

Not comparable
Gemini 3.1 Pro
Not measured
GPT-5.4
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
Gemini 3.1 Pro
Not measured
GPT-5.4
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
GPT-5.4
$0.01
Fits in one request

Gemini 3.1 Pro 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
GPT-5.4
$0.17
Fits in one request

Gemini 3.1 Pro 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
GPT-5.4
$0.25
Fits in one request

Gemini 3.1 Pro 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

GPT-5.4

$0.25 per 1M cached input tokens

OpenAI pricing

Reasoning profile

Gemini 3.1 Pro

Reasoning

GPT-5.4

Reasoning

Weight access

Gemini 3.1 Pro

Proprietary

GPT-5.4

Proprietary

License

Gemini 3.1 Pro

Proprietary

GPT-5.4

Proprietary

Release date

Gemini 3.1 Pro

2026-02-19

GPT-5.4

2026-03-05

If you already use one of these models
Deployment change
The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal
GPT-5.4 has the higher public score estimate, 72.89 versus 56.49, but the 90% score intervals overlap.
Workload cost
Repository review: $0.136 vs $0.17. Cache-heavy agent loop: $0.2 vs $0.25.
Context tradeoff
GPT-5.4 has the larger documented window (1.05M).

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 evidence37 rows

Agentic

  • Claw-Eval

    Shared source
    Gemini 3.1 Pro57.8%
    GPT-5.460.3%

    GPT-5.4 leads this result

  • DeepSearchQA

    Shared source
    Gemini 3.1 Pro69.7%
    GPT-5.473.6%

    GPT-5.4 leads this result

  • τ²-bench results

    Gemini 3.1 Pro95.6%
    Source
    GPT-5.498.9%
    Source

    GPT-5.4 leads this result

  • Gert Labs

    Shared source
    Gemini 3.1 Pro56.87%
    GPT-5.464.89%

    GPT-5.4 leads this result

  • ResearchClawBench

    Shared source
    Gemini 3.1 Pro13.3%
    GPT-5.415.3%

    GPT-5.4 leads this result

  • Terminal-Bench 2.0

    Gemini 3.1 Pro—
    GPT-5.475.1%
    Source

    Not directly comparable

  • CyberGym

    Gemini 3.1 Pro—
    GPT-5.479.0%
    Source

    Not directly comparable

  • BrowseComp

    Gemini 3.1 Pro—
    GPT-5.482.7%
    Source

    Not directly comparable

  • OSWorld-Verified

    Gemini 3.1 Pro—
    GPT-5.475%
    Source

    Not directly comparable

  • MCP Atlas

    Gemini 3.1 Pro—
    GPT-5.470.6%
    Source

    Not directly comparable

  • Toolathlon

    Gemini 3.1 Pro—
    GPT-5.454.6%
    Source

    Not directly comparable

  • JobBench

    Gemini 3.1 Pro—
    GPT-5.438.9%
    Source

    Not directly comparable

  • ExploitGym

    Gemini 3.1 Pro—
    GPT-5.46.0%
    Source

    Not directly comparable

Coding

  • LiveCodeBench Pro

    Shared source
    Gemini 3.1 Pro82.9%
    GPT-5.487.5%

    GPT-5.4 leads this result

  • React Native Evals

    Shared source
    Gemini 3.1 Pro78.9%
    GPT-5.485.3%

    GPT-5.4 leads this result

  • Vibe Code Bench

    Shared source
    Gemini 3.1 Pro32.03%
    GPT-5.467.42%

    GPT-5.4 leads this result

  • SWE-bench Pro

    Gemini 3.1 Pro—
    GPT-5.457.7%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    Gemini 3.1 Pro77.1%
    Source
    GPT-5.474.0%
    Source

    Gemini 3.1 Pro leads this result

  • ARC-AGI-3

    Shared source
    Gemini 3.1 Pro0.4%
    GPT-5.40.2%

    Gemini 3.1 Pro leads this result

Knowledge

  • GPQA-D

    Shared source
    Gemini 3.1 Pro94.3%
    GPT-5.492.8%

    Gemini 3.1 Pro leads this result

  • HLE w/o tools

    Gemini 3.1 Pro45.4%
    Source
    GPT-5.439.8%
    Source

    Gemini 3.1 Pro leads this result

  • HealthBench Hard

    Shared source
    Gemini 3.1 Pro20.6%
    GPT-5.440.1%

    GPT-5.4 leads this result

  • MedXpertQA (Text)

    Shared source
    Gemini 3.1 Pro71.5%
    GPT-5.459.6%

    Gemini 3.1 Pro leads this result

  • GPQA

    Gemini 3.1 Pro—
    GPT-5.492.8%
    Source

    Not directly comparable

  • HLE

    Gemini 3.1 Pro—
    GPT-5.452.1%
    Source

    Not directly comparable

  • HealthBench Professional

    Gemini 3.1 Pro—
    GPT-5.448.1%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Gemini 3.1 Pro36.900%
    GPT-5.447.600%

    GPT-5.4 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Gemini 3.1 Pro16.700%
    GPT-5.427.100%

    GPT-5.4 leads this result

Multimodal

  • MMMU-Pro

    Gemini 3.1 Pro83.9%
    Source
    GPT-5.481.2%
    Source

    Gemini 3.1 Pro leads this result

  • CharXiv

    Shared source
    Gemini 3.1 Pro80.2%
    GPT-5.482.8%

    GPT-5.4 leads this result

  • ERQA

    Shared source
    Gemini 3.1 Pro69.4%
    GPT-5.465.4%

    Gemini 3.1 Pro leads this result

  • SimpleVQA

    Shared source
    Gemini 3.1 Pro72.4%
    GPT-5.461.1%

    Gemini 3.1 Pro leads this result

  • ScreenSpot Pro

    Shared source
    Gemini 3.1 Pro84.4%
    GPT-5.485.4%

    GPT-5.4 leads this result

  • ZeroBench

    Shared source
    Gemini 3.1 Pro29.0%
    GPT-5.441.0%

    GPT-5.4 leads this result

  • MedXpertQA (MM)

    Shared source
    Gemini 3.1 Pro81.3%
    GPT-5.477.1%

    Gemini 3.1 Pro leads this result

  • OfficeQA Pro

    Gemini 3.1 Pro—
    GPT-5.453.2%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    Gemini 3.1 Pro—
    GPT-5.482.1%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Gemini 3.1 Pro or GPT-5.4?

GPT-5.4 has the higher public score estimate, 72.89 versus 56.49, 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 GPT-5.4?

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 GPT-5.4?

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 GPT-5.4?

For the stated presets, chat costs $0.008 on Gemini 3.1 Pro and $0.01 on GPT-5.4; repository review costs $0.136 and $0.17; the cache-heavy agent loop costs $0.2 and $0.25. Costs use the listed standard API rates.

Which has the larger context window, Gemini 3.1 Pro or GPT-5.4?

GPT-5.4 has the larger documented context window: 1.05M, compared with 1M.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated September 3, 2026

Watch Gemini 3.1 Pro vs GPT-5.4

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

Read a sample issue

Join 2,000+ readers.