ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Opus 4 vs DeepSeek-R1 vs o3-pro

Too close to call on our weighted score (o3-pro 52, DeepSeek-R1 50, Claude Opus 4 50). The right pick depends on what you value most.

Price in rating: Included · Exclude price

  1. Anthropic

    Claude Opus 4

    Released May 22, 2025

    50/100
    • ECI142.9
    • Price$15.00 / $75.00
    • Context200K
  2. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    50/100
    • ECI138.6
    • Price$1.02 / $5.14
    • Context128K
  3. OpenAI

    o3-pro

    Released Jun 10, 2025

    52/100
    • ECI147.5
    • Price$20.00 / $80.00
    • Context200K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (o3-pro 52/100, DeepSeek-R1 50/100, Claude Opus 4 50/100), so choose by what matters most for your work: o3-pro for raw capability and DeepSeek-R1 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • Capabilityo3-proCapabilities Index (ECI): o3-pro 147.5 · Claude Opus 4 142.9 · DeepSeek-R1 138.6
  • Lowest priceDeepSeek-R1DeepSeek-R1 $2.05 · Claude Opus 4 $30.00 · o3-pro $35.00 per 1M tokens (3:1 blend)
  • Longest contextClaude Opus 4 and o3-proClaude Opus 4 200,000 · o3-pro 200,000 · DeepSeek-R1 128,000 tokens
  • Widest inputsClaude Opus 4Claude Opus 4: Text, Images, PDFs · DeepSeek-R1: Text · o3-pro: Text, Images
  • Self-hostingDeepSeek-R1Publishes downloadable weights
How the score is built
MeasureWeightClaude Opus 4DeepSeek-R1o3-pro
CapabilityCapabilities Index (ECI)50%716775
Price25%0340
Inputs & features15%703570
Context window10%393239
Overall100%50/10050/10052/100
02 — Side by side

Every spec in one table

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

Claude Opus 4 vs DeepSeek-R1 vs o3-pro specifications side by side
SpecificationClaude Opus 4AnthropicDeepSeek-R1DeepSeeko3-proOpenAI
Capability
Capabilities Index (ECI)142.9138.6147.5 (best)
ECI rank#101 of 158#118 of 158#79 of 158 (best)
GPQA DiamondGraduate-level science questions76.3% (best)71.7%—
OTIS Mock AIME 2024–2025Competition mathematics64.4% (best)53.3%—
SWE-bench VerifiedFixing real GitHub issues70.7%——
Price per million tokens
Input$15.00$1.02 (best)$20.00
Output$75.00$5.14 (best)$80.00
Cached input———
Blended (3:1)$30.00$2.05 (best)$35.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 7 providersMedian of 12 providersOfficial OpenAI API
Limits
Context window200,000 tokens (best)128,000 tokens200,000 tokens (best)
Max output32,000 tokens32,768 tokens100,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYeslow · medium · high
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsProprietaryOpenProprietary
API model ID——o3-pro
API providers813 (best)10
ReleasedMay 22, 2025Jan 20, 2025Jun 10, 2025
Knowledge cutoffMar 31, 2025Jul 2024May 2024
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.

  • Claude Opus 4$300.00
  • DeepSeek-R1$20.53
  • o3-pro$360.00
04 — Questions

Which should you choose?

Which is better: Claude Opus 4, DeepSeek-R1 or o3-pro?

It is close. Our weighted score puts them within 2 points (o3-pro 52/100, DeepSeek-R1 50/100, Claude Opus 4 50/100), so choose by what matters most for your work: o3-pro for raw capability and DeepSeek-R1 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Opus 4, DeepSeek-R1 or o3-pro?

DeepSeek-R1 is cheaper at $1.02 input / $5.14 output per million tokens (median across 12 API providers). Claude Opus 4 costs $15.00 input / $75.00 output per million tokens (median across 7 API providers); o3-pro costs $20.00 input / $80.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $2.05 per million tokens for DeepSeek-R1 versus $30.00 for Claude Opus 4 (15× as much) and $35.00 for o3-pro (17× as much).

Which scores higher on benchmarks?

o3-pro scores higher on the Capabilities Index (ECI): o3-pro 147.5 (#79 of 158), Claude Opus 4 142.9 (#101 of 158) and DeepSeek-R1 138.6 (#118 of 158). Their confidence ranges do not overlap (145.6–149.4 vs 141.3–144.5), so the gap is a real one.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-R1 and o3-pro yet, so there is no like-for-like coding score. On overall capability, o3-pro 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?

Claude Opus 4 and o3-pro have the largest context windows (200,000 and 200,000 tokens), against 128,000 for DeepSeek-R1. Maximum output per response: Claude Opus 4 up to 32,000, DeepSeek-R1 up to 32,768, o3-pro up to 100,000 tokens.

Which can read images, PDFs, audio or video?

Claude Opus 4 accepts text, images and PDFs; DeepSeek-R1 accepts text; o3-pro accepts text and images. Claude Opus 4 handles the widest range of inputs.

Are any of these open source?

DeepSeek-R1 publishes its weights and can be self-hosted; Claude Opus 4 and o3-pro is proprietary.

Which is newer?

o3-pro is the newest, released Jun 10, 2025. Claude Opus 4 came out May 22, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: Claude Opus 4 Mar 31, 2025, DeepSeek-R1 Jul 2024, o3-pro May 2024.

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.