ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-4.1 vs Mistral Large 2407 vs Claude Sonnet 3.5 v2

GPT-4.1 comes out ahead, 65 to 58 and 48 on our weighted score, though Mistral Large 2407 is 14% cheaper per token.

Price in rating: Excluded · Include price

  1. Our pick

    OpenAI

    GPT-4.1

    Released Apr 14, 2025

    65/100
    • ECI136.2
    • Price$2.00 / $8.00
    • Context1.05M
  2. Mistral AI

    Mistral Large 2407

    Released Jul 24, 2024

    48/100
    • ECI126.4
    • Price$2.00 / $6.00
    • Context131K
  3. Anthropic

    Claude Sonnet 3.5 v2

    Released Oct 22, 2024

    58/100
    • 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 65/100 against Claude Sonnet 3.5 v2 (58) and Mistral Large 2407 (48). It leads on capability, inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityGPT-4.1Capabilities Index (ECI): GPT-4.1 136.2 · Claude Sonnet 3.5 v2 133.3 · Mistral Large 2407 126.4
  • Lowest priceMistral Large 2407Mistral Large 2407 $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 2407 131,072 tokens
  • Widest inputsGPT-4.1 and Claude Sonnet 3.5 v2GPT-4.1: Text, Images, PDFs · Mistral Large 2407: Text, PDFs · Claude Sonnet 3.5 v2: Text, Images, PDFs
  • Self-hostingMistral Large 2407Publishes downloadable weights
How the score is built
MeasureWeightGPT-4.1Mistral Large 2407Claude Sonnet 3.5 v2
CapabilityCapabilities Index (ECI)67%645562
Inputs & features20%703560
Context window13%653239
Overall100%65/10048/10058/100
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 2407 vs Claude Sonnet 3.5 v2 specifications side by side
SpecificationGPT-4.1OpenAIMistral Large 2407Mistral AIClaude Sonnet 3.5 v2Anthropic
Capability
Capabilities Index (ECI)136.2 (best)126.4133.3
ECI rank#123 of 158 (best)#143 of 158#131 of 158
GPQA DiamondGraduate-level science questions66.9% (best)49.0%55.3%
FrontierMath Tiers 1–3Research-level mathematics6.0%——
OTIS Mock AIME 2024–2025Competition mathematics38.3% (best)8.5%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 5 providersMedian of 2 providers
Limits
Context window1,047,576 tokens (best)131,072 tokens200,000 tokens
Max output32,768 tokens104,857 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesYesYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputYesNoNo
Availability
WeightsProprietaryOpenProprietary
API model IDgpt-4.1——
API providers32 (best)53
ReleasedApr 14, 2025Jul 24, 2024Oct 22, 2024
Knowledge cutoffApr 2024Mar 31, 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 2407$32.00
  • Claude Sonnet 3.5 v2$56.00
04 — Questions

Which should you choose?

Which is better: GPT-4.1, Mistral Large 2407 or Claude Sonnet 3.5 v2?

GPT-4.1 is the better all-round choice, scoring 65/100 against Claude Sonnet 3.5 v2 (58) and Mistral Large 2407 (48). It leads on capability, inputs & features and context window. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, GPT-4.1, Mistral Large 2407 or Claude Sonnet 3.5 v2?

Mistral Large 2407 is cheaper at $2.00 input / $6.00 output per million tokens (median across 5 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 2407 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?

GPT-4.1 scores higher on the Capabilities Index (ECI): GPT-4.1 136.2 (#123 of 158), Claude Sonnet 3.5 v2 133.3 (#131 of 158) and Mistral Large 2407 126.4 (#143 of 158). The confidence ranges of the top two overlap (134.1–138.1 vs 131.0–135.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — GPT-4.1 66.9%, Claude Sonnet 3.5 v2 55.3%, Mistral Large 2407 49.0%; OTIS Mock AIME 2024–2025 — GPT-4.1 38.3%, Mistral Large 2407 8.5%, Claude Sonnet 3.5 v2 8.5%.

Which is better for coding?

There are no published SWE-bench Verified results for Mistral Large 2407 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 2407. Maximum output per response: GPT-4.1 up to 32,768, Mistral Large 2407 up to 104,857, 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 2407 accepts text and PDFs; 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 2407 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. Claude Sonnet 3.5 v2 came out Oct 22, 2024; Mistral Large 2407 came out Jul 24, 2024. Knowledge cutoff: GPT-4.1 Apr 2024, Mistral Large 2407 Mar 31, 2024, Claude Sonnet 3.5 v2 Apr 30, 2024.

How do you decide the winner?

This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, 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.