Skip to main content
BenchLM
Data

Gemini 4 Argon vs GPT-4.1

Updated November 13, 2026. Rank says Gemini 4 Argon is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Share or export
Share on XLinkedInAPI/MCP

Decision reading

Gemini 4 Argon has the higher public score, 79.03 versus 36.26, and the 90% score intervals do not overlap. 1 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A
Google logo
Gemini 4 Argon

Google

79.03/100

Supported · Public rank #8

90% interval 75.4–82.7

Model B
OpenAI logo
GPT-4.1

OpenAI

36.26/100

Supported · Public rank #150

90% interval 20.3–52.2

API price per 1M tokens

Gemini 4 Argon: $2 input / $10 output

GPT-4.1: $2 input / $8 output

Context window

Gemini 4 Argon: 1M

GPT-4.1: 1M

Released

Gemini 4 Argon: September 30, 2026

GPT-4.1: April 14, 2025

Shared results
1
Gemini 4 Argon only
38
GPT-4.1 only
9
Like-for-like categories
1 / 8
Supported: Gemini 4 Argon and GPT-4.1How the comparison works

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

    GPT-4.1

    GPT-4.1 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 4 Argon

    Gemini 4 Argon 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-4.1

    GPT-4.1 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

    GPT-4.1 is not ranked on the public lane for coding, so no winner is named for coding.

    Confidence: limited

  • Agentic work

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

    Not enough matched evidence

    GPT-4.1 is not ranked on the public lane for agentic, so no winner is named for agentic.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

Which one for a specific job

Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

71.8Gemini 4 Argon—GPT-4.1

Not comparable · BenchAlign v5.8

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboardShortlist models for this job
Same basis rules as the category table below

Or describe your own job

The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.

Describe the task and constraints. This selector recommends models; it cannot carry out the task or access your files and accounts.

We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy

What is actually comparable

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

1 category rests on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.

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.

  • FrontierMath v2 (Tiers 1-3)Math

    Normalized gap 80.0
    Gemini 4 Argon:85.965%
    GPT-4.1:5.965%
    Shared source
Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, reasoning, multimodal, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Knowledge

Like-for-like
Gemini 4 Argon
79.2
Supported · #8/180
GPT-4.1
33.0
Supported · #140/180
Basis
BenchAlign v5.8 lane · 2 vs 4 public rows
Reading
Gemini 4 Argon leads

Reasoning

Directional only
Gemini 4 Argon
76.5
Supported · #7/160
GPT-4.1
25.5
Estimated · #135/160
Basis
BenchAlign v5.8 lane · 7 vs 0 public rows
Reading
Directional only

Agentic

Not comparable
Gemini 4 Argon
74.9
Supported · #6/135
GPT-4.1
Not ranked
Basis
BenchAlign v5.8 lane · 13 vs 1 public rows
Reading
Not comparable

Coding

Not comparable
Gemini 4 Argon
71.8
Supported · #9/162
GPT-4.1
Not ranked
Basis
BenchAlign v5.8 lane · 9 vs 2 public rows
Reading
Not comparable

Multimodal

Not comparable
Gemini 4 Argon
Not ranked
GPT-4.1
Not ranked
Basis
BenchAlign v5.8 lane · 5 vs 0 public rows
Reading
Not comparable

Multilingual

Not comparable
Gemini 4 Argon
Not ranked
GPT-4.1
61.5
#14/17
Basis
Provisional lane · 0 vs 1 weighted rows
Reading
Not comparable

Instruction following

Not comparable
Gemini 4 Argon
Not ranked
GPT-4.1
50.3
#99/157
Basis
Provisional lane · 0 vs 0 weighted rows
Reading
Not comparable

Math

Not comparable
Gemini 4 Argon
87.4
Unranked · 2 rankable rows
GPT-4.1
23.4
Unranked · 1 rankable row
Basis
Provisional lane · 2 vs 1 weighted rows
Reading
Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, reasoning, multimodal, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

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 4 Argon
$0.007
Fits in one request
GPT-4.1
$0.006
Fits in one request

GPT-4.1 has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Gemini 4 Argon
$0.13
Fits in one request
GPT-4.1
$0.124
Fits in one request

GPT-4.1 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 4 Argon
$0.16
Fits in one request
GPT-4.1
$0.52
Fits in one request
Cached input priced at the published list-input rate

Gemini 4 Argon has the lower modeled cost

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

Your workload

Enter a month of tokens to price it at both models’ listed API rates.

Gemini 4 Argon
$40.00
per month
GPT-4.1
$36.00
per month

Standard listed rates, no batch or volume discounts.

Cached input falls back to the list input rate only where a cached rate is unpublished

Price against score, among all priced models

Overall score against output price per 1M tokens, one model per family. Pricing as of November 12, 2026.

Gemini 4 ArgonGPT-4.1

20406080100$0.10$0.50$1$5$10$50$100Output price, $ per 1M tokens (log)Overall score
  • 2 models at the same price score higher than Gemini 4 Argon. The nearest is Gemini 4 Carbon (score 89.2, also $10.00 per 1M output tokens).
  • 42 models score at least as high as GPT-4.1 for the same price or less. The nearest is o3 (score 48.0, also $8.00 per 1M output tokens).

Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.

See GPT-4.1 on the full price vs performance chart

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 4 Argon

$0.1 per 1M cached input tokens

Google Gemini API pricing

GPT-4.1

Not published

Reasoning profile

Gemini 4 Argon

Reasoning

GPT-4.1

Non-Reasoning

Weight access

Gemini 4 Argon

Proprietary

GPT-4.1

Proprietary

License

Gemini 4 Argon

Proprietary

GPT-4.1

Proprietary

Release date

Gemini 4 Argon

2026-09-30

GPT-4.1

2025-04-14

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
Gemini 4 Argon has the higher public score, 79.03 versus 36.26, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.13 vs $0.124. Cache-heavy agent loop: $0.16 vs $0.52.
Context tradeoff
Both models list 1M.
Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, Gemini 4 Argon or GPT-4.1?

Gemini 4 Argon has the higher public score, 79.03 versus 36.26, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, Gemini 4 Argon or GPT-4.1?

GPT-4.1 is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, Gemini 4 Argon or GPT-4.1?

GPT-4.1 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, Gemini 4 Argon or GPT-4.1?

For the stated presets, chat costs $0.007 on Gemini 4 Argon and $0.006 on GPT-4.1; repository review costs $0.13 and $0.124; the cache-heavy agent loop costs $0.16 and $0.52. GPT-4.1 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Gemini 4 Argon or GPT-4.1?

Both models list the same context window, 1M.

Benchmark evidence

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

Browse raw public benchmark evidence48 rows

Agentic

  • AutomationBench

    Gemini 4 Argon51.3%
    Source
    GPT-4.1—

    Not directly comparable

  • Finance Agent v2

    Gemini 4 Argon65.4%
    Source
    GPT-4.1—

    Not directly comparable

  • Terminal-Bench 4.0

    Gemini 4 Argon57.40%
    Source
    GPT-4.1—

    Not directly comparable

  • Agents' Last Exam

    Gemini 4 Argon39.5%
    Source
    GPT-4.1—

    Not directly comparable

  • OSWorld 2.0

    Gemini 4 Argon69.2%
    Source
    GPT-4.1—

    Not directly comparable

  • CWE-bench v1

    Gemini 4 Argon68.0%
    Source
    GPT-4.1—

    Not directly comparable

  • Terminal-Bench-Science 0.1 (6x verifier timeout)

    Gemini 4 Argon57.6%
    Source
    GPT-4.1—

    Not directly comparable

  • MazeBench

    Gemini 4 Argon12%
    Source
    GPT-4.1—

    Not directly comparable

  • OSWorld 2.1 Offline

    Gemini 4 Argon74.7%
    Source
    GPT-4.1—

    Not directly comparable

  • ExploitGym

    Gemini 4 Argon39.5%
    Source
    GPT-4.1—

    Not directly comparable

  • RoboDojo Sim

    Gemini 4 Argon34.2%
    Source
    GPT-4.1—

    Not directly comparable

  • CWE-bench

    Gemini 4 Argon65.0%
    Source
    GPT-4.1—

    Not directly comparable

  • Terminal-Bench 2.1 (Vals)

    Gemini 4 Argon57.7%
    Source
    GPT-4.1—

    Not directly comparable

  • Gert Labs

    Gemini 4 Argon—
    GPT-4.125.65%
    Source

    Not directly comparable

Coding

  • ScarfBench

    Gemini 4 Argon75.2%
    Source
    GPT-4.1—

    Not directly comparable

  • DeepSWE

    Gemini 4 Argon77.9%
    Source
    GPT-4.1—

    Not directly comparable

  • FrontierSWE v2

    Gemini 4 Argon55.0%
    Source
    GPT-4.1—

    Not directly comparable

  • Vibe Code Bench

    Gemini 4 Argon91.90%
    Source
    GPT-4.1—

    Not directly comparable

  • PostTrainBench v1.1

    Gemini 4 Argon45.3%
    Source
    GPT-4.1—

    Not directly comparable

  • Bug Hunt Bench

    Gemini 4 Argon40.7 fixes
    Source
    GPT-4.1—

    Not directly comparable

  • FrontierCode 2.0

    Gemini 4 Argon26.3%
    Source
    GPT-4.1—

    Not directly comparable

  • CursorBench 4.0

    Gemini 4 Argon52.9%
    Source
    GPT-4.1—

    Not directly comparable

  • PostTrainBench

    Gemini 4 Argon40.4%
    Source
    GPT-4.1—

    Not directly comparable

  • SWE-bench Verified

    Gemini 4 Argon—
    GPT-4.154.6%
    Source

    Not directly comparable

  • LiveCodeBench (Vals)

    Gemini 4 Argon—
    GPT-4.154.7%
    Source

    Not directly comparable

Reasoning

  • STEMBench

    Gemini 4 Argon2.44
    Source
    GPT-4.1—

    Not directly comparable

  • Graphwalks BFS 128K

    Gemini 4 Argon99.7%
    Source
    GPT-4.1—

    Not directly comparable

  • GraphWalks BFS 256K–1M

    Gemini 4 Argon84.2%
    Source
    GPT-4.1—

    Not directly comparable

  • ARC-AGI-1

    Gemini 4 Argon98.50%
    Source
    GPT-4.1—

    Not directly comparable

  • ARC-AGI-2

    Gemini 4 Argon91.3%
    Source
    GPT-4.1—

    Not directly comparable

  • ARC-AGI-3

    Gemini 4 Argon46.3%
    Source
    GPT-4.1—

    Not directly comparable

  • ARC-AGI-3 Provider Adapter

    Gemini 4 Argon97.30%
    Source
    GPT-4.1—

    Not directly comparable

Multimodal

  • ParseBench-2

    Gemini 4 Argon84.20%
    Source
    GPT-4.1—

    Not directly comparable

  • ExtractBench Pro

    Gemini 4 Argon30%
    Source
    GPT-4.1—

    Not directly comparable

  • Chartography (no tools)

    Gemini 4 Argon71.6%
    Source
    GPT-4.1—

    Not directly comparable

  • LVBench

    Gemini 4 Argon91.7%
    Source
    GPT-4.1—

    Not directly comparable

  • Blueprint-Bench 2

    Gemini 4 Argon54.4%
    Source
    GPT-4.1—

    Not directly comparable

Knowledge

  • LABBench2

    Gemini 4 Argon88.8%
    Source
    GPT-4.1—

    Not directly comparable

  • Morphology-to-molecule matching

    Gemini 4 Argon25.2%
    Source
    GPT-4.1—

    Not directly comparable

  • MMLU

    Gemini 4 Argon—
    GPT-4.190.2%
    Source

    Not directly comparable

  • GPQA

    Gemini 4 Argon—
    GPT-4.166.3%
    Source

    Not directly comparable

  • GPQA Diamond (Vals)

    Gemini 4 Argon—
    GPT-4.165.4%
    Source

    Not directly comparable

  • MMLU-Pro (Vals)

    Gemini 4 Argon—
    GPT-4.180.5%
    Source

    Not directly comparable

Multilingual

  • MMLU-ProX

    Gemini 4 Argon—
    GPT-4.172.7%
    Source

    Not directly comparable

Instruction following

  • Gray Swan IPI (15 attempts)

    Gemini 4 Argon0.7%
    Source
    GPT-4.1—

    Not directly comparable

  • IFEval

    Gemini 4 Argon—
    GPT-4.187.4%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Gemini 4 Argon85.965%
    GPT-4.15.965%

    Gemini 4 Argon leads this result

  • FrontierMath v2 (Tier 4)

    Gemini 4 Argon78.049%
    Source
    GPT-4.1—

    Not directly comparable

48 public results · 1 shared

Related comparisons

Compare API pricingRead the methodologyOpen the model selector

Watch Gemini 4 Argon vs GPT-4.1

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

Read a sample issue

Join 7,000+ subscribers.

Last updated November 13, 2026