ZMIME
Comparison · 2 models · Updated Oct 4, 2026

GPT-5.4 vs Claude Sonnet 5

Too close to call on our weighted score (Claude Sonnet 5 66, GPT-5.4 65). The right pick depends on what you value most.

  1. OpenAI

    GPT-5.4

    Released Mar 5, 2026

    65/100
    • ECI156.9
    • Price$2.50 / $15.00
    • Context1.05M
    Full specs Remove GPT-5.4

  2. Anthropic

    Claude Sonnet 5

    Released Jun 30, 2026

    66/100
    • ECI156.3
    • Price$2.00 / $10.00
    • Context1M
    Full specs Remove Claude Sonnet 5

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Too close to call

It is close. Our weighted score puts them within 1 points (Claude Sonnet 5 66/100, GPT-5.4 65/100), so choose by what matters most for your work: GPT-5.4 for raw capability and Claude Sonnet 5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT-5.4Capabilities Index (ECI): GPT-5.4 156.9 · Claude Sonnet 5 156.3
  • Lowest priceClaude Sonnet 5Claude Sonnet 5 $4.00 · GPT-5.4 $5.63 per 1M tokens (3:1 blend)
  • Longest contextGPT-5.4GPT-5.4 1,050,000 · Claude Sonnet 5 1,000,000 tokens
  • Widest inputsSame inputsGPT-5.4: Text, Images, PDFs · Claude Sonnet 5: Text, Images, PDFs
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightGPT-5.4Claude Sonnet 5
CapabilityCapabilities Index (ECI)50%8786
Price25%1421
Inputs & features15%8080
Context window10%6160
Overall100%65/10066/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

GPT-5.4 vs Claude Sonnet 5 specifications side by side
SpecificationGPT-5.4OpenAIClaude Sonnet 5Anthropic
Capability
Capabilities Index (ECI)156.9 (best)156.3
ECI rank#16 of 148 (best)#23 of 148
GPQA DiamondGraduate-level science questions93.3% (best)90.5%
FrontierMath Tiers 1–3Research-level mathematics78.6% (best)65.6%
OTIS Mock AIME 2024–2025Competition mathematics97.8% (best)94.7%
SWE-bench VerifiedFixing real GitHub issues76.9%—
SimpleQA VerifiedShort factual questions45.1% (best)33.7%
Price per million tokens
Input$2.50$2.00 (best)
Output$15.00$10.00 (best)
Cached input$0.25$0.20 (best)
Blended (3:1)$5.63$4.00 (best)
Long-context rateOver 272K: $5.00 / $22.50Same rate
Price sourceOfficial OpenAI APIOfficial Anthropic API
Limits
Context window1,050,000 tokens (best)1,000,000 tokens
Max output128,000 tokens128,000 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsYesYes
AudioNoNo
VideoNoNo
ReasoningYeslow · medium · high · xhighYeslow · medium · high · xhigh · max
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model IDgpt-5.4claude-sonnet-5
API providers3638 (best)
ReleasedMar 5, 2026Jun 30, 2026
Knowledge cutoffAug 31, 2025Jan 31, 2026
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • GPT-5.4$55.00
  • Claude Sonnet 5$40.00
04 — Questions

Which should you choose?

Which is better: GPT-5.4 or Claude Sonnet 5?

It is close. Our weighted score puts them within 1 points (Claude Sonnet 5 66/100, GPT-5.4 65/100), so choose by what matters most for your work: GPT-5.4 for raw capability and Claude Sonnet 5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-5.4 or Claude Sonnet 5?

Claude Sonnet 5 is cheaper at $2.00 input / $10.00 output per million tokens (official Anthropic API price). GPT-5.4 costs $2.50 input / $15.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $4.00 per million tokens for Claude Sonnet 5 versus $5.63 for GPT-5.4 (1.4× as much).

Which scores higher on benchmarks?

GPT-5.4 scores higher on the Capabilities Index (ECI): GPT-5.4 156.9 (#16 of 148) and Claude Sonnet 5 156.3 (#23 of 148). The confidence ranges of the top two overlap (154.9–159.1 vs 153.6–158.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — GPT-5.4 93.3%, Claude Sonnet 5 90.5%; FrontierMath Tiers 1–3 — GPT-5.4 78.6%, Claude Sonnet 5 65.6%; OTIS Mock AIME 2024–2025 — GPT-5.4 97.8%, Claude Sonnet 5 94.7%; SimpleQA Verified — GPT-5.4 45.1%, Claude Sonnet 5 33.7%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Sonnet 5 yet, so there is no like-for-like coding score. On overall capability, GPT-5.4 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

GPT-5.4 has the largest context window at 1,050,000 tokens, against 1,000,000 for Claude Sonnet 5. Maximum output per response: GPT-5.4 up to 128,000, Claude Sonnet 5 up to 128,000 tokens.

Which can read images, PDFs, audio or video?

GPT-5.4 accepts text, images and PDFs; Claude Sonnet 5 accepts text, images and PDFs. They handle the same number of input types.

Are any of these open source?

No. GPT-5.4 and Claude Sonnet 5 are proprietary and only available through APIs and apps.

Which is newer?

Claude Sonnet 5 is the newest, released Jun 30, 2026. GPT-5.4 came out Mar 5, 2026. Knowledge cutoff: GPT-5.4 Aug 31, 2025, Claude Sonnet 5 Jan 31, 2026.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons