ZMIME
Comparison · 3 models · Updated Nov 18, 2026

o1 vs GPT-4.1 vs Claude Opus 4

GPT-4.1 comes out ahead, 55 to 50 and 50 on our weighted score, and it is the cheaper option too.

Price in rating: Included · Exclude price

  1. OpenAI

    o1

    Released Dec 5, 2024Deprecated

    50/100
    • ECI141.2
    • Price$15.00 / $60.00
    • Context200K
  2. Our pick

    OpenAI

    GPT-4.1

    Released Apr 14, 2025

    55/100
    • ECI136.2
    • Price$2.00 / $8.00
    • Context1.05M
  3. Anthropic

    Claude Opus 4

    Released May 22, 2025

    50/100
    • ECI142.9
    • Price$15.00 / $75.00
    • Context200K
01 — Verdict

GPT-4.1 is our pick

GPT-4.1 is the better all-round choice, scoring 55/100 against o1 (50) and Claude Opus 4 (50). It leads on price and context window. o1 wins on inputs & features. Claude Opus 4 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityClaude Opus 4Capabilities Index (ECI): Claude Opus 4 142.9 · o1 141.2 · GPT-4.1 136.2
  • Lowest priceGPT-4.1GPT-4.1 $3.50 · o1 $26.25 · Claude Opus 4 $30.00 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1GPT-4.1 1,047,576 · o1 200,000 · Claude Opus 4 200,000 tokens
  • Widest inputsSame inputso1: Text, Images, PDFs · GPT-4.1: Text, Images, PDFs · Claude Opus 4: Text, Images, PDFs
  • Self-hostingNo confirmed open weightsAll three are available only through APIs
How the score is built
MeasureWeighto1GPT-4.1Claude Opus 4
CapabilityCapabilities Index (ECI)50%696471
Price25%0230
Inputs & features15%807070
Context window10%396539
Overall100%50/10055/10050/100
02 — Side by side

Every spec in one table

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

o1 vs GPT-4.1 vs Claude Opus 4 specifications side by side
Specificationo1OpenAIGPT-4.1OpenAIClaude Opus 4Anthropic
Capability
Capabilities Index (ECI)141.2136.2142.9 (best)
ECI rank#109 of 158#123 of 158#101 of 158 (best)
GPQA DiamondGraduate-level science questions76.8% (best)66.9%76.3%
FrontierMath Tiers 1–3Research-level mathematics14.7% (best)6.0%—
OTIS Mock AIME 2024–2025Competition mathematics73.3% (best)38.3%64.4%
SWE-bench VerifiedFixing real GitHub issues—48.5%70.7% (best)
SimpleQA VerifiedShort factual questions41.1% (best)31.1%—
Price per million tokens
Input$15.00$2.00 (best)$15.00
Output$60.00$8.00 (best)$75.00
Cached input$7.50$0.50 (best)—
Blended (3:1)$26.25$3.50 (best)$30.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIOfficial OpenAI APIMedian of 7 providers
Limits
Context window200,000 tokens1,047,576 tokens (best)200,000 tokens
Max output100,000 tokens (best)32,768 tokens32,000 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesYesYes
AudioNoNoNo
VideoNoNoNo
ReasoningYeslow · medium · highNoYes
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryProprietary
API model IDo1gpt-4.1—
API providers932 (best)8
ReleasedDec 5, 2024Apr 14, 2025May 22, 2025
Knowledge cutoffSep 2023Apr 2024Mar 31, 2025
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.

  • o1$270.00
  • GPT-4.1$36.00
  • Claude Opus 4$300.00
04 — Questions

Which should you choose?

Which is better: o1, GPT-4.1 or Claude Opus 4?

GPT-4.1 is the better all-round choice, scoring 55/100 against o1 (50) and Claude Opus 4 (50). It leads on price and context window. o1 wins on inputs & features. Claude Opus 4 wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, o1, GPT-4.1 or Claude Opus 4?

GPT-4.1 is cheaper at $2.00 input / $8.00 output per million tokens (official OpenAI API price). o1 costs $15.00 input / $60.00 output per million tokens (official OpenAI API price); Claude Opus 4 costs $15.00 input / $75.00 output per million tokens (median across 7 API providers). At a typical mix of three input tokens to one output token, that is $3.50 per million tokens for GPT-4.1 versus $26.25 for o1 (7.5× as much) and $30.00 for Claude Opus 4 (8.6× as much).

Which scores higher on benchmarks?

Claude Opus 4 scores higher on the Capabilities Index (ECI): Claude Opus 4 142.9 (#101 of 158), o1 141.2 (#109 of 158) and GPT-4.1 136.2 (#123 of 158). The confidence ranges of the top two overlap (141.3–144.5 vs 139.5–142.8), so treat the gap as small. On individual benchmarks: GPQA Diamond — o1 76.8%, Claude Opus 4 76.3%, GPT-4.1 66.9%; OTIS Mock AIME 2024–2025 — o1 73.3%, Claude Opus 4 64.4%, GPT-4.1 38.3%.

Which is better for coding?

There are no published SWE-bench Verified results for o1 yet, so there is no like-for-like coding score. On overall capability, Claude Opus 4 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.

Which has the bigger context window?

GPT-4.1 has the largest context window at 1,047,576 tokens, against 200,000 for o1 and 200,000 for Claude Opus 4. Maximum output per response: o1 up to 100,000, GPT-4.1 up to 32,768, Claude Opus 4 up to 32,000 tokens.

Which can read images, PDFs, audio or video?

o1 accepts text, images and PDFs; GPT-4.1 accepts text, images and PDFs; Claude Opus 4 accepts text, images and PDFs. They handle the same number of input types.

Are any of these open source?

No. o1, GPT-4.1 and Claude Opus 4 are proprietary and only available through APIs and apps.

Which is newer?

Claude Opus 4 is the newest, released May 22, 2025. GPT-4.1 came out Apr 14, 2025; o1 came out Dec 5, 2024. Knowledge cutoff: o1 Sep 2023, GPT-4.1 Apr 2024, Claude Opus 4 Mar 31, 2025.

How do you decide the winner?

This rating uses 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 Nov 18, 2026.