ZMIME
Comparison · 3 models · Updated Nov 18, 2026

GPT-4o vs Mistral Large 2407 vs Claude Sonnet 3.5 v2

Too close to call on our weighted score (Claude Sonnet 3.5 v2 58, GPT-4o 56, Mistral Large 2407 48). The right pick depends on what you value most.

Price in rating: Excluded · Include price

  1. OpenAI

    GPT-4o

    Released May 13, 2024

    56/100
    • ECI128.1
    • Price$2.50 / $10.00
    • Context128K
  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

Too close to call

It is close. Our weighted score puts them within 2 points (Claude Sonnet 3.5 v2 58/100, GPT-4o 56/100, Mistral Large 2407 48/100), so choose by what matters most for your work: Claude Sonnet 3.5 v2 for raw capability and Mistral Large 2407 on price. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityClaude Sonnet 3.5 v2Capabilities Index (ECI): Claude Sonnet 3.5 v2 133.3 · GPT-4o 128.1 · Mistral Large 2407 126.4
  • Lowest priceMistral Large 2407Mistral Large 2407 $3.00 · GPT-4o $4.38 · Claude Sonnet 3.5 v2 $5.60 per 1M tokens (3:1 blend)
  • Longest contextClaude Sonnet 3.5 v2Claude Sonnet 3.5 v2 200,000 · Mistral Large 2407 131,072 · GPT-4o 128,000 tokens
  • Widest inputsGPT-4o and Claude Sonnet 3.5 v2GPT-4o: 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-4oMistral Large 2407Claude Sonnet 3.5 v2
CapabilityCapabilities Index (ECI)67%575562
Inputs & features20%703560
Context window13%323239
Overall100%56/10048/10058/100
02 — Side by side

Every spec in one table

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

GPT-4o vs Mistral Large 2407 vs Claude Sonnet 3.5 v2 specifications side by side
SpecificationGPT-4oOpenAIMistral Large 2407Mistral AIClaude Sonnet 3.5 v2Anthropic
Capability
Capabilities Index (ECI)128.1126.4133.3 (best)
ECI rank#139 of 158#143 of 158#131 of 158 (best)
GPQA DiamondGraduate-level science questions48.9%49.0%55.3% (best)
OTIS Mock AIME 2024–2025Competition mathematics6.3%8.5% (best)8.5% (best)
Price per million tokens
Input$2.50$2.00 (best)$2.80
Output$10.00$6.00 (best)$14.00
Cached input$1.25——
Blended (3:1)$4.38$3.00 (best)$5.60
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIMedian of 5 providersMedian of 2 providers
Limits
Context window128,000 tokens131,072 tokens200,000 tokens (best)
Max output16,384 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-4o——
API providers27 (best)53
ReleasedMay 13, 2024Jul 24, 2024Oct 22, 2024
Knowledge cutoffSep 2023Mar 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-4o$45.00
  • Mistral Large 2407$32.00
  • Claude Sonnet 3.5 v2$56.00
04 — Questions

Which should you choose?

Which is better: GPT-4o, Mistral Large 2407 or Claude Sonnet 3.5 v2?

It is close. Our weighted score puts them within 2 points (Claude Sonnet 3.5 v2 58/100, GPT-4o 56/100, Mistral Large 2407 48/100), so choose by what matters most for your work: Claude Sonnet 3.5 v2 for raw capability and Mistral Large 2407 on price. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, GPT-4o, 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-4o costs $2.50 input / $10.00 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 $4.38 for GPT-4o (1.5× as much) and $5.60 for Claude Sonnet 3.5 v2 (1.9× as much).

Which scores higher on benchmarks?

Claude Sonnet 3.5 v2 scores higher on the Capabilities Index (ECI): Claude Sonnet 3.5 v2 133.3 (#131 of 158), GPT-4o 128.1 (#139 of 158) and Mistral Large 2407 126.4 (#143 of 158). Their confidence ranges do not overlap (131.0–135.5 vs 125.4–130.7), so the gap is a real one. On individual benchmarks: GPQA Diamond — Claude Sonnet 3.5 v2 55.3%, Mistral Large 2407 49.0%, GPT-4o 48.9%; OTIS Mock AIME 2024–2025 — Mistral Large 2407 8.5%, Claude Sonnet 3.5 v2 8.5%, GPT-4o 6.3%.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-4o, Mistral Large 2407 and Claude Sonnet 3.5 v2 yet, so there is no like-for-like coding score. On overall capability, Claude Sonnet 3.5 v2 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 Sonnet 3.5 v2 has the largest context window at 200,000 tokens, against 131,072 for Mistral Large 2407 and 128,000 for GPT-4o. Maximum output per response: GPT-4o up to 16,384, 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-4o accepts text, images and PDFs; Mistral Large 2407 accepts text and PDFs; Claude Sonnet 3.5 v2 accepts text, images and PDFs. GPT-4o handles the widest range of inputs.

Are any of these open source?

Mistral Large 2407 publishes its weights and can be self-hosted; GPT-4o and Claude Sonnet 3.5 v2 is proprietary.

Which is newer?

Claude Sonnet 3.5 v2 is the newest, released Oct 22, 2024. Mistral Large 2407 came out Jul 24, 2024; GPT-4o came out May 13, 2024. Knowledge cutoff: GPT-4o Sep 2023, 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.