ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-4o vs DeepSeek-R1 vs Mistral Large 2407

DeepSeek-R1 comes out ahead, 50 to 47 and 42 on our weighted score, and it is the cheaper option too.

Price in rating: Included · Exclude price

  1. OpenAI

    GPT-4o

    Released May 13, 2024

    47/100
    • ECI128.1
    • Price$2.50 / $10.00
    • Context128K
  2. Our pick

    DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

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

    Mistral Large 2407

    Released Jul 24, 2024

    42/100
    • ECI126.4
    • Price$2.00 / $6.00
    • Context131K
01 — Verdict

DeepSeek-R1 is our pick

DeepSeek-R1 is the better all-round choice, scoring 50/100 against GPT-4o (47) and Mistral Large 2407 (42). It leads on capability and price. GPT-4o wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityDeepSeek-R1Capabilities Index (ECI): DeepSeek-R1 138.6 · GPT-4o 128.1 · Mistral Large 2407 126.4
  • Lowest priceDeepSeek-R1DeepSeek-R1 $2.05 · Mistral Large 2407 $3.00 · GPT-4o $4.38 per 1M tokens (3:1 blend)
  • Longest contextMistral Large 2407Mistral Large 2407 131,072 · GPT-4o 128,000 · DeepSeek-R1 128,000 tokens
  • Widest inputsGPT-4oGPT-4o: Text, Images, PDFs · DeepSeek-R1: Text · Mistral Large 2407: Text, PDFs
  • Self-hostingDeepSeek-R1 and Mistral Large 2407Publishes downloadable weights
How the score is built
MeasureWeightGPT-4oDeepSeek-R1Mistral Large 2407
CapabilityCapabilities Index (ECI)50%576755
Price25%193426
Inputs & features15%703535
Context window10%323232
Overall100%47/10050/10042/100
02 — Side by side

Every spec in one table

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

GPT-4o vs DeepSeek-R1 vs Mistral Large 2407 specifications side by side
SpecificationGPT-4oOpenAIDeepSeek-R1DeepSeekMistral Large 2407Mistral AI
Capability
Capabilities Index (ECI)128.1138.6 (best)126.4
ECI rank#139 of 158#118 of 158 (best)#143 of 158
GPQA DiamondGraduate-level science questions48.9%71.7% (best)49.0%
OTIS Mock AIME 2024–2025Competition mathematics6.3%53.3% (best)8.5%
Price per million tokens
Input$2.50$1.02 (best)$2.00
Output$10.00$5.14 (best)$6.00
Cached input$1.25——
Blended (3:1)$4.38$2.05 (best)$3.00
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIMedian of 12 providersMedian of 5 providers
Limits
Context window128,000 tokens128,000 tokens131,072 tokens (best)
Max output16,384 tokens32,768 tokens104,857 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenOpen
API model IDgpt-4o——
API providers27 (best)135
ReleasedMay 13, 2024Jan 20, 2025Jul 24, 2024
Knowledge cutoffSep 2023Jul 2024Mar 31, 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.

  • GPT-4o$45.00
  • DeepSeek-R1$20.53
  • Mistral Large 2407$32.00
04 — Questions

Which should you choose?

Which is better: GPT-4o, DeepSeek-R1 or Mistral Large 2407?

DeepSeek-R1 is the better all-round choice, scoring 50/100 against GPT-4o (47) and Mistral Large 2407 (42). It leads on capability and price. GPT-4o wins on inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-4o, DeepSeek-R1 or Mistral Large 2407?

DeepSeek-R1 is cheaper at $1.02 input / $5.14 output per million tokens (median across 12 API providers). Mistral Large 2407 costs $2.00 input / $6.00 output per million tokens (median across 5 API providers); GPT-4o costs $2.50 input / $10.00 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 $3.00 for Mistral Large 2407 (1.5× as much) and $4.38 for GPT-4o (2.1× as much).

Which scores higher on benchmarks?

DeepSeek-R1 scores higher on the Capabilities Index (ECI): DeepSeek-R1 138.6 (#118 of 158), GPT-4o 128.1 (#139 of 158) and Mistral Large 2407 126.4 (#143 of 158). Their confidence ranges do not overlap (136.7–140.4 vs 125.4–130.7), so the gap is a real one. On individual benchmarks: GPQA Diamond — DeepSeek-R1 71.7%, Mistral Large 2407 49.0%, GPT-4o 48.9%; OTIS Mock AIME 2024–2025 — DeepSeek-R1 53.3%, Mistral Large 2407 8.5%, GPT-4o 6.3%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-4o, DeepSeek-R1 and Mistral Large 2407 yet, so there is no like-for-like coding score. On overall capability, DeepSeek-R1 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?

Mistral Large 2407 has the largest context window at 131,072 tokens, against 128,000 for GPT-4o and 128,000 for DeepSeek-R1. Maximum output per response: GPT-4o up to 16,384, DeepSeek-R1 up to 32,768, Mistral Large 2407 up to 104,857 tokens.

Which can read images, PDFs, audio or video?

GPT-4o accepts text, images and PDFs; DeepSeek-R1 accepts text; Mistral Large 2407 accepts text and PDFs. GPT-4o handles the widest range of inputs.

Are any of these open source?

DeepSeek-R1 and Mistral Large 2407 publishes its weights and can be self-hosted; GPT-4o is proprietary.

Which is newer?

DeepSeek-R1 is the newest, released Jan 20, 2025. Mistral Large 2407 came out Jul 24, 2024; GPT-4o came out May 13, 2024. Knowledge cutoff: GPT-4o Sep 2023, DeepSeek-R1 Jul 2024, Mistral Large 2407 Mar 31, 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.