ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-4.1 vs Mistral Large 2.1 vs Claude Sonnet 3.5 v2

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. Mistral AI

    Mistral Large 2.1

    Released Nov 18, 2024

    28/100
    • ECI—
    • Price$2.00 / $6.00
    • Context131K
  3. Anthropic

    Claude Sonnet 3.5 v2

    Released Oct 22, 2024

    32/100
    • ECI133.3
    • Price$2.80 / $14.00
    • Context200K
01 — Verdict

GPT-4.1 is our pick

GPT-4.1 is the better all-round choice, scoring 49/100 against Claude Sonnet 3.5 v2 (32) and Mistral Large 2.1 (28). It leads on capability, inputs & features 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% · Claude Sonnet 3.5 v2 31.9% · Mistral Large 2.1 29.6%
  • Lowest priceMistral Large 2.1Mistral Large 2.1 $3.00 · GPT-4.1 $3.50 · Claude Sonnet 3.5 v2 $5.60 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1GPT-4.1 1,047,576 · Claude Sonnet 3.5 v2 200,000 · Mistral Large 2.1 131,072 tokens
  • Widest inputsGPT-4.1 and Claude Sonnet 3.5 v2GPT-4.1: Text, Images, PDFs · Mistral Large 2.1: Text · Claude Sonnet 3.5 v2: Text, Images, PDFs
  • Self-hostingMistral Large 2.1Publishes downloadable weights
How the score is built
MeasureWeightGPT-4.1Mistral Large 2.1Claude Sonnet 3.5 v2
CapabilityShared benchmarks50%533032
Price25%232614
Inputs & features15%702560
Context window10%653239
Overall100%49/10028/10032/100
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 Mistral Large 2.1 vs Claude Sonnet 3.5 v2 specifications side by side
SpecificationGPT-4.1OpenAIMistral Large 2.1Mistral AIClaude Sonnet 3.5 v2Anthropic
Capability
Capabilities Index (ECI)136.2 (best)—133.3
ECI rank#123 of 158 (best)—#131 of 158
GPQA DiamondGraduate-level science questions66.9% (best)51.3%55.3%
FrontierMath Tiers 1–3Research-level mathematics6.0%——
OTIS Mock AIME 2024–2025Competition mathematics38.3% (best)7.8%8.5%
SWE-bench VerifiedFixing real GitHub issues48.5%——
SimpleQA VerifiedShort factual questions31.1%——
Price per million tokens
Input$2.00 (best)$2.00 (best)$2.80
Output$8.00$6.00 (best)$14.00
Cached input$0.50——
Blended (3:1)$3.50$3.00 (best)$5.60
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIMedian of 2 providersMedian of 2 providers
Limits
Context window1,047,576 tokens (best)131,072 tokens200,000 tokens
Max output32,768 tokens (best)16,384 tokens8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenProprietary
API model IDgpt-4.1——
API providers32 (best)23
ReleasedApr 14, 2025Nov 18, 2024Oct 22, 2024
Knowledge cutoffApr 2024Nov 2024Apr 30, 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
  • Mistral Large 2.1$32.00
  • Claude Sonnet 3.5 v2$56.00
04 — Questions

Which should you choose?

Which is better: GPT-4.1, Mistral Large 2.1 or Claude Sonnet 3.5 v2?

GPT-4.1 is the better all-round choice, scoring 49/100 against Claude Sonnet 3.5 v2 (32) and Mistral Large 2.1 (28). It leads on capability, inputs & features 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, Mistral Large 2.1 or Claude Sonnet 3.5 v2?

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); Claude Sonnet 3.5 v2 costs $2.80 input / $14.00 output per million tokens (median across 2 API providers). 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 $5.60 for Claude Sonnet 3.5 v2 (1.9× 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%, Claude Sonnet 3.5 v2 31.9% and Mistral Large 2.1 29.6%. On individual benchmarks: GPQA Diamond — GPT-4.1 66.9%, Claude Sonnet 3.5 v2 55.3%, Mistral Large 2.1 51.3%; OTIS Mock AIME 2024–2025 — GPT-4.1 38.3%, Claude Sonnet 3.5 v2 8.5%, Mistral Large 2.1 7.8%.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Large 2.1 and Claude Sonnet 3.5 v2 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 200,000 for Claude Sonnet 3.5 v2 and 131,072 for Mistral Large 2.1. Maximum output per response: GPT-4.1 up to 32,768, Mistral Large 2.1 up to 16,384, Claude Sonnet 3.5 v2 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

GPT-4.1 accepts text, images and PDFs; Mistral Large 2.1 accepts text; Claude Sonnet 3.5 v2 accepts text, images and PDFs. 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 Claude Sonnet 3.5 v2 is proprietary.

Which is newer?

GPT-4.1 is the newest, released Apr 14, 2025. Mistral Large 2.1 came out Nov 18, 2024; Claude Sonnet 3.5 v2 came out Oct 22, 2024. Knowledge cutoff: GPT-4.1 Apr 2024, Mistral Large 2.1 Nov 2024, Claude Sonnet 3.5 v2 Apr 30, 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.