Skip to main content
BenchLM
Advertise

Model comparison

GPT-4.1 vs GPT-5.4 mini

Updated July 31, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

GPT-4.1

OpenAI

50.4/100

Supported · Public rank #111

90% interval 30.8–70.0

GPT-5.4 mini

OpenAI

55.8/100

Estimated · Public rank #82

90% interval 44.3–67.3

GPT-5.4 mini has the higher public score estimate, 55.84 versus 50.4, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

3 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-4.1

    GPT-4.1 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.4 mini

    GPT-5.4 mini 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

    GPT-5.4 mini

    GPT-5.4 mini has the lower estimated token cost for this stated workload. GPT-4.1 has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    GPT-5.4 mini

    GPT-5.4 mini 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
3
GPT-4.1 only
4
GPT-5.4 mini only
11
Like-for-like categories
1 / 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
GPT-4.1
4.1
GPT-5.4 mini
21.7
Weighted basis
2 vs 2 rows
Reading
GPT-5.4 mini leads

Knowledge

Directional only
GPT-4.1
66.3
GPT-5.4 mini
47.8
Weighted basis
1 vs 2 rows
Reading
Directional only

Agentic

Not comparable
GPT-4.1
Not measured
GPT-5.4 mini
65.7
Weighted basis
0 vs 2 rows
Reading
Not comparable

Coding

Not comparable
GPT-4.1
54.6
GPT-5.4 mini
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
GPT-4.1
Not measured
GPT-5.4 mini
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
GPT-4.1
Not measured
GPT-5.4 mini
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
GPT-4.1
Not measured
GPT-5.4 mini
76.6
Weighted basis
0 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
GPT-4.1
87.4
GPT-5.4 mini
Not measured
Weighted basis
1 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

GPT-4.1
$0.006
Fits in one request
GPT-5.4 mini
$0.003
Fits in one request

GPT-5.4 mini has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-4.1
$0.124
Fits in one request
GPT-5.4 mini
$0.051
Fits in one request

GPT-5.4 mini has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

GPT-4.1
$0.52
Fits in one request
Cached input priced at the published list-input rate
GPT-5.4 mini
$0.075
Fits in one request

GPT-5.4 mini has the lower modeled cost

GPT-4.1 has no published cached-input rate, so cached tokens use its listed input rate.

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.

GPT-4.1

Not published

GPT-5.4 mini

$0.075 per 1M cached input tokens

OpenAI pricing

Provider availability

GPT-4.1

Not sourced

GPT-5.4 mini

Generally Available · OpenAI Responses API

OpenAI model catalog

Reasoning profile

GPT-4.1

Non-Reasoning

GPT-5.4 mini

Reasoning

Weight access

GPT-4.1

Proprietary

GPT-5.4 mini

Proprietary

License

GPT-4.1

Proprietary

GPT-5.4 mini

Proprietary

Release date

GPT-4.1

2025-04-14

GPT-5.4 mini

2026-03-17

If you already use one of these models
Deployment change
Both entries list OpenAI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
GPT-5.4 mini has the higher public score estimate, 55.84 versus 50.4, but the 90% score intervals overlap.
Workload cost
Repository review: $0.124 vs $0.051. Cache-heavy agent loop: $0.52 vs $0.075.
Context tradeoff
GPT-4.1 has the larger documented window (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 evidence18 rows

Agentic

  • Gert Labs

    GPT-4.125.65%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • Terminal-Bench 2.0

    GPT-4.1—
    GPT-5.4 mini60%
    Source

    Not directly comparable

  • OSWorld-Verified

    GPT-4.1—
    GPT-5.4 mini72.1%
    Source

    Not directly comparable

  • MCP Atlas

    GPT-4.1—
    GPT-5.4 mini57.7%
    Source

    Not directly comparable

  • Toolathlon

    GPT-4.1—
    GPT-5.4 mini42.9%
    Source

    Not directly comparable

  • τ²-bench results

    GPT-4.1—
    GPT-5.4 mini93.4%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    GPT-4.154.6%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • Vibe Code Bench

    GPT-4.1—
    GPT-5.4 mini47.97%
    Source

    Not directly comparable

  • FrontierCode 1.1 Main

    GPT-4.1—
    GPT-5.4 mini27.0%
    Source

    Not directly comparable

Knowledge

  • MMLU

    GPT-4.190.2%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • GPQA

    GPT-4.166.3%
    Source
    GPT-5.4 mini88%
    Source

    GPT-5.4 mini leads this result

  • HLE

    GPT-4.1—
    GPT-5.4 mini41.5%
    Source

    Not directly comparable

  • HLE w/o tools

    GPT-4.1—
    GPT-5.4 mini28.2%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    GPT-4.15.517%
    GPT-5.4 mini28.280%

    GPT-5.4 mini leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    GPT-4.10.000%
    GPT-5.4 mini2.080%

    GPT-5.4 mini leads this result

Multimodal

  • MMMU-Pro

    GPT-4.1—
    GPT-5.4 mini76.6%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    GPT-4.1—
    GPT-5.4 mini78%
    Source

    Not directly comparable

Instruction following

  • IFEval

    GPT-4.187.4%
    Source
    GPT-5.4 mini—

    Not directly comparable

Frequently asked questions

Which is better, GPT-4.1 or GPT-5.4 mini?

GPT-5.4 mini has the higher public score estimate, 55.84 versus 50.4, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, GPT-4.1 or GPT-5.4 mini?

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, GPT-4.1 or GPT-5.4 mini?

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, GPT-4.1 or GPT-5.4 mini?

For the stated presets, chat costs $0.006 on GPT-4.1 and $0.003 on GPT-5.4 mini; repository review costs $0.124 and $0.051; the cache-heavy agent loop costs $0.52 and $0.075. GPT-4.1 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-4.1 or GPT-5.4 mini?

GPT-4.1 has the larger documented context window: 1M, compared with 400K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated July 31, 2026

Watch GPT-4.1 vs GPT-5.4 mini

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

Read a sample issue

Join 2,000+ readers.