Skip to main content
BenchLM
Advertise

Model comparison

Claude Sonnet 4.6 vs GPT-5.4 nano

Updated July 30, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload.

Claude Sonnet 4.6

Anthropic

64.3/100

Supported · Public rank #35

90% interval 52.0–76.7

GPT-5.4 nano

OpenAI

66.0/100

Supported · Public rank #28

90% interval 55.5–76.4

GPT-5.4 nano has the higher public score estimate, 65.98 versus 64.3, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

7 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.

  • Agentic work

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

    Claude Sonnet 4.6

    Claude Sonnet 4.6 leads on the same 2 weighted benchmark rows.

    Confidence: limited

  • Long documents

    Prompts that approach the documented context limit

    GPT-5.4 nano

    GPT-5.4 nano has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.4 nano

    GPT-5.4 nano 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

    GPT-5.4 nano

    GPT-5.4 nano 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

  • Cache-heavy agent loop cost

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

    Not enough matched evidence

    The page does not recommend a cost winner because at least one model cannot fit the stated workload in one request. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.

    Confidence: rate-fallback

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
7
Claude Sonnet 4.6 only
13
GPT-5.4 nano only
6
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.

Agentic

Like-for-like
Claude Sonnet 4.6
65.2
GPT-5.4 nano
42.9
Weighted basis
2 vs 2 rows
Reading
Claude Sonnet 4.6 leads

Math

Like-for-like
Claude Sonnet 4.6
26.4
GPT-5.4 nano
21.0
Weighted basis
2 vs 2 rows
Reading
Claude Sonnet 4.6 leads

Knowledge

Directional only
Claude Sonnet 4.6
66.0
GPT-5.4 nano
43.8
Weighted basis
4 vs 2 rows
Reading
Directional only

Coding

Not comparable
Claude Sonnet 4.6
69.1
GPT-5.4 nano
Not measured
Weighted basis
2 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
Claude Sonnet 4.6
Not measured
GPT-5.4 nano
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
Claude Sonnet 4.6
Not measured
GPT-5.4 nano
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Multimodal

Not comparable
Claude Sonnet 4.6
77.4
GPT-5.4 nano
66.1
Weighted basis
1 vs 1 rows
Reading
Not comparable

Instruction following

Not comparable
Claude Sonnet 4.6
Not measured
GPT-5.4 nano
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

Claude Sonnet 4.6
$0.0105
Fits in one request
GPT-5.4 nano
$0.00082
Fits in one request

GPT-5.4 nano has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

Claude Sonnet 4.6
$0.195
Fits in one request
GPT-5.4 nano
$0.01375
Fits in one request

GPT-5.4 nano has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

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

Claude Sonnet 4.6
$0.81
Does not fit in one request
Cached input priced at the published list-input rate
GPT-5.4 nano
$0.0205
Fits in one request

Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 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.

Claude Sonnet 4.6

Not published

GPT-5.4 nano

$0.02 per 1M cached input tokens

OpenAI pricing

Provider availability

Claude Sonnet 4.6

Not sourced

GPT-5.4 nano

Generally Available · OpenAI Responses API

OpenAI model catalog

Reasoning profile

Claude Sonnet 4.6

Non-Reasoning

GPT-5.4 nano

Reasoning

Weight access

Claude Sonnet 4.6

Proprietary

GPT-5.4 nano

Proprietary

License

Claude Sonnet 4.6

Proprietary

GPT-5.4 nano

Proprietary

Release date

Claude Sonnet 4.6

2026-02-01

GPT-5.4 nano

2026-03-17

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 nano has the higher public score estimate, 65.98 versus 64.3, but the 90% score intervals overlap.
Workload cost
Repository review: $0.195 vs $0.01375. Cache-heavy agent loop: $0.81 vs $0.0205.
Context tradeoff
GPT-5.4 nano has the larger documented window (400K).

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 evidence26 rows

Agentic

  • Terminal-Bench 2.0

    Claude Sonnet 4.659.1%
    Source
    GPT-5.4 nano46.3%
    Source

    Claude Sonnet 4.6 leads this result

  • OSWorld-Verified

    Claude Sonnet 4.672.1%
    Source
    GPT-5.4 nano39%
    Source

    Claude Sonnet 4.6 leads this result

  • Claw-Eval

    Claude Sonnet 4.667.8%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • CyberGym

    Claude Sonnet 4.665.2%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • Gert Labs

    Claude Sonnet 4.662.92%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • OSWorld 2.0

    Claude Sonnet 4.68.3%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • JobBench

    Claude Sonnet 4.636.9%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • MCP Atlas

    Claude Sonnet 4.6—
    GPT-5.4 nano56.1%
    Source

    Not directly comparable

  • Toolathlon

    Claude Sonnet 4.6—
    GPT-5.4 nano35.5%
    Source

    Not directly comparable

  • τ²-bench results

    Claude Sonnet 4.6—
    GPT-5.4 nano92.5%
    Source

    Not directly comparable

Coding

  • SWE-bench Verified

    Claude Sonnet 4.679.6%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • SWE-Rebench

    Claude Sonnet 4.660.7%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • React Native Evals

    Claude Sonnet 4.680.6%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • Vibe Code Bench

    Shared source
    Claude Sonnet 4.651.48%
    GPT-5.4 nano26.10%

    Claude Sonnet 4.6 leads this result

  • cursorBench31

    Claude Sonnet 4.648.8%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • FrontierCode 1.1 Main

    Claude Sonnet 4.624.3%
    Source
    GPT-5.4 nano—

    Not directly comparable

Knowledge

  • GPQA

    Claude Sonnet 4.689.9%
    Source
    GPT-5.4 nano82.8%
    Source

    Claude Sonnet 4.6 leads this result

  • SuperGPQA

    Claude Sonnet 4.695%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • MMLU-Pro

    Claude Sonnet 4.679.2%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • HLE

    Claude Sonnet 4.649%
    Source
    GPT-5.4 nano37.7%
    Source

    Claude Sonnet 4.6 leads this result

  • HLE w/o tools

    Claude Sonnet 4.6—
    GPT-5.4 nano24.3%
    Source

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    Claude Sonnet 4.632.400%
    GPT-5.4 nano25.860%

    Claude Sonnet 4.6 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    Claude Sonnet 4.68.300%
    GPT-5.4 nano6.250%

    Claude Sonnet 4.6 leads this result

Multimodal

  • CharXiv

    Claude Sonnet 4.677.4%
    Source
    GPT-5.4 nano—

    Not directly comparable

  • MMMU-Pro

    Claude Sonnet 4.6—
    GPT-5.4 nano66.1%
    Source

    Not directly comparable

  • MMMU-Pro w/ Python

    Claude Sonnet 4.6—
    GPT-5.4 nano69.5%
    Source

    Not directly comparable

Frequently asked questions

Which is better, Claude Sonnet 4.6 or GPT-5.4 nano?

GPT-5.4 nano has the higher public score estimate, 65.98 versus 64.3, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, Claude Sonnet 4.6 or GPT-5.4 nano?

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, Claude Sonnet 4.6 or GPT-5.4 nano?

Claude Sonnet 4.6 leads the like-for-like agentic tasks comparison across 2 shared weighted benchmark rows.

Which costs less, Claude Sonnet 4.6 or GPT-5.4 nano?

For the stated presets, chat costs $0.0105 on Claude Sonnet 4.6 and $0.00082 on GPT-5.4 nano; repository review costs $0.195 and $0.01375; the cache-heavy agent loop costs $0.81 and $0.0205. Claude Sonnet 4.6 does not fit this workload in one request. Claude Sonnet 4.6 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, Claude Sonnet 4.6 or GPT-5.4 nano?

GPT-5.4 nano has the larger documented context window: 400K, compared with 200K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated July 30, 2026

Watch Claude Sonnet 4.6 vs GPT-5.4 nano

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

Read a sample issue

Join 2,000+ readers.