ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-4.1 vs GPT-4o vs Mistral Large 2.1

GPT-4.1 comes out ahead, 49 to 32 and 28 on our weighted score, though Mistral Large 2.1 is 14% cheaper per token.

Price in rating: Included · Exclude price

  1. Our pick

    OpenAI

    GPT-4.1

    Released Apr 14, 2025

    49/100
    • ECI136.2
    • Price$2.00 / $8.00
    • Context1.05M
  2. OpenAI

    GPT-4o

    Released May 13, 2024

    32/100
    • ECI128.1
    • Price$2.50 / $10.00
    • Context128K
  3. Mistral AI

    Mistral Large 2.1

    Released Nov 18, 2024

    28/100
    • ECI—
    • Price$2.00 / $6.00
    • Context131K
01 — Verdict

GPT-4.1 is our pick

GPT-4.1 is the better all-round choice, scoring 49/100 against GPT-4o (32) and Mistral Large 2.1 (28). It leads on capability and context window. Mistral Large 2.1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Mistral Large 2.1 has no Capabilities Index score yet.

  • CapabilityGPT-4.1Shared benchmarks: GPT-4.1 52.6% · Mistral Large 2.1 29.6% · GPT-4o 27.6%
  • Lowest priceMistral Large 2.1Mistral Large 2.1 $3.00 · GPT-4.1 $3.50 · GPT-4o $4.38 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1GPT-4.1 1,047,576 · Mistral Large 2.1 131,072 · GPT-4o 128,000 tokens
  • Widest inputsGPT-4.1 and GPT-4oGPT-4.1: Text, Images, PDFs · GPT-4o: Text, Images, PDFs · Mistral Large 2.1: Text
  • Self-hostingMistral Large 2.1Publishes downloadable weights
How the score is built
MeasureWeightGPT-4.1GPT-4oMistral Large 2.1
CapabilityShared benchmarks50%532830
Price25%231926
Inputs & features15%707025
Context window10%653232
Overall100%49/10032/10028/100
02 — Side by side

Every spec in one table

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

GPT-4.1 vs GPT-4o vs Mistral Large 2.1 specifications side by side
SpecificationGPT-4.1OpenAIGPT-4oOpenAIMistral Large 2.1Mistral AI
Capability
Capabilities Index (ECI)136.2 (best)128.1—
ECI rank#123 of 158 (best)#139 of 158—
GPQA DiamondGraduate-level science questions66.9% (best)48.9%51.3%
FrontierMath Tiers 1–3Research-level mathematics6.0%——
OTIS Mock AIME 2024–2025Competition mathematics38.3% (best)6.3%7.8%
SWE-bench VerifiedFixing real GitHub issues48.5%——
SimpleQA VerifiedShort factual questions31.1%——
Price per million tokens
Input$2.00 (best)$2.50$2.00 (best)
Output$8.00$10.00$6.00 (best)
Cached input$0.50 (best)$1.25—
Blended (3:1)$3.50$4.38$3.00 (best)
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIOfficial OpenAI APIMedian of 2 providers
Limits
Context window1,047,576 tokens (best)128,000 tokens131,072 tokens
Max output32,768 tokens (best)16,384 tokens16,384 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryProprietaryOpen
API model IDgpt-4.1gpt-4o—
API providers32 (best)272
ReleasedApr 14, 2025May 13, 2024Nov 18, 2024
Knowledge cutoffApr 2024Sep 2023Nov 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-4.1$36.00
  • GPT-4o$45.00
  • Mistral Large 2.1$32.00
04 — Questions

Which should you choose?

Which is better: GPT-4.1, GPT-4o or Mistral Large 2.1?

GPT-4.1 is the better all-round choice, scoring 49/100 against GPT-4o (32) and Mistral Large 2.1 (28). It leads on capability and context window. Mistral Large 2.1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%. Capability uses the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025), because Mistral Large 2.1 has no Capabilities Index score yet.

Which is cheaper, GPT-4.1, GPT-4o or Mistral Large 2.1?

Mistral Large 2.1 is cheaper at $2.00 input / $6.00 output per million tokens (median across 2 API providers). GPT-4.1 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price); 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 $3.00 per million tokens for Mistral Large 2.1 versus $3.50 for GPT-4.1 (1.2× as much) and $4.38 for GPT-4o (1.5× as much).

Which scores higher on benchmarks?

Not every model here has a Capabilities Index score, so we compare the average of shared benchmarks (GPQA Diamond and OTIS Mock AIME 2024–2025): GPT-4.1 52.6%, Mistral Large 2.1 29.6% and GPT-4o 27.6%. On individual benchmarks: GPQA Diamond — GPT-4.1 66.9%, Mistral Large 2.1 51.3%, GPT-4o 48.9%; OTIS Mock AIME 2024–2025 — GPT-4.1 38.3%, Mistral Large 2.1 7.8%, GPT-4o 6.3%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-4o and Mistral Large 2.1 yet, so there is no like-for-like coding score. On overall capability, GPT-4.1 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 131,072 for Mistral Large 2.1 and 128,000 for GPT-4o. Maximum output per response: GPT-4.1 up to 32,768, GPT-4o up to 16,384, Mistral Large 2.1 up to 16,384 tokens.

Which can read images, PDFs, audio or video?

GPT-4.1 accepts text, images and PDFs; GPT-4o accepts text, images and PDFs; Mistral Large 2.1 accepts text. GPT-4.1 handles the widest range of inputs.

Are any of these open source?

Mistral Large 2.1 publishes its weights and can be self-hosted; GPT-4.1 and GPT-4o is proprietary.

Which is newer?

GPT-4.1 is the newest, released Apr 14, 2025. Mistral Large 2.1 came out Nov 18, 2024; GPT-4o came out May 13, 2024. Knowledge cutoff: GPT-4.1 Apr 2024, GPT-4o Sep 2023, Mistral Large 2.1 Nov 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.