ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek-R1 vs Mistral Medium 3.5 vs Claude Sonnet 3.7

Mistral Medium 3.5 comes out ahead, 56 to 52 and 50 on our weighted score, though DeepSeek-R1 is 32% cheaper per token.

Price in rating: Included · Exclude price

  1. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    50/100
    • ECI138.6
    • Price$1.02 / $5.14
    • Context128K
  2. Our pick

    Mistral AI

    Mistral Medium 3.5

    Released Apr 29, 2026

    56/100
    • ECI141.6
    • Price$1.50 / $7.50
    • Context262K
  3. Anthropic

    Claude Sonnet 3.7

    Released Feb 19, 2025

    52/100
    • ECI141.1
    • Price$3.00 / $15.00
    • Context200K
01 — Verdict

Mistral Medium 3.5 is our pick

Mistral Medium 3.5 is the better all-round choice, scoring 56/100 against Claude Sonnet 3.7 (52) and DeepSeek-R1 (50). It leads on context window. DeepSeek-R1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityMistral Medium 3.5Capabilities Index (ECI): Mistral Medium 3.5 141.6 · Claude Sonnet 3.7 141.1 · DeepSeek-R1 138.6
  • Lowest priceDeepSeek-R1DeepSeek-R1 $2.05 · Mistral Medium 3.5 $3.00 · Claude Sonnet 3.7 $6.00 per 1M tokens (3:1 blend)
  • Longest contextMistral Medium 3.5Mistral Medium 3.5 262,144 · Claude Sonnet 3.7 200,000 · DeepSeek-R1 128,000 tokens
  • Widest inputsClaude Sonnet 3.7DeepSeek-R1: Text · Mistral Medium 3.5: Text, Images · Claude Sonnet 3.7: Text, Images, PDFs
  • Self-hostingDeepSeek-R1 and Mistral Medium 3.5Publishes downloadable weights
How the score is built
MeasureWeightDeepSeek-R1Mistral Medium 3.5Claude Sonnet 3.7
CapabilityCapabilities Index (ECI)50%676969
Price25%342612
Inputs & features15%357070
Context window10%324339
Overall100%50/10056/10052/100
02 — Side by side

Every spec in one table

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

DeepSeek-R1 vs Mistral Medium 3.5 vs Claude Sonnet 3.7 specifications side by side
SpecificationDeepSeek-R1DeepSeekMistral Medium 3.5Mistral AIClaude Sonnet 3.7Anthropic
Capability
Capabilities Index (ECI)138.6141.6 (best)141.1
ECI rank#118 of 158#107 of 158 (best)#110 of 158
GPQA DiamondGraduate-level science questions71.7%—79.7% (best)
OTIS Mock AIME 2024–2025Competition mathematics53.3%—57.8% (best)
SWE-bench VerifiedFixing real GitHub issues——61.0%
Price per million tokens
Input$1.02 (best)$1.50$3.00
Output$5.14 (best)$7.50$15.00
Cached input—$0.15—
Blended (3:1)$2.05 (best)$3.00$6.00
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 12 providersOfficial Mistral APIMedian of 3 providers
Limits
Context window128,000 tokens262,144 tokens (best)200,000 tokens
Max output32,768 tokens262,144 tokens (best)64,000 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningYesYeshighYes
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenOpenProprietary
API model ID—mistral-medium-2604—
API providers1316 (best)4
ReleasedJan 20, 2025Apr 29, 2026Feb 19, 2025
Knowledge cutoffJul 2024—Oct 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.

  • DeepSeek-R1$20.53
  • Mistral Medium 3.5$30.00
  • Claude Sonnet 3.7$60.00
04 — Questions

Which should you choose?

Which is better: DeepSeek-R1, Mistral Medium 3.5 or Claude Sonnet 3.7?

Mistral Medium 3.5 is the better all-round choice, scoring 56/100 against Claude Sonnet 3.7 (52) and DeepSeek-R1 (50). It leads on context window. DeepSeek-R1 wins on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, DeepSeek-R1, Mistral Medium 3.5 or Claude Sonnet 3.7?

DeepSeek-R1 is cheaper at $1.02 input / $5.14 output per million tokens (median across 12 API providers). Mistral Medium 3.5 costs $1.50 input / $7.50 output per million tokens (official Mistral API price); Claude Sonnet 3.7 costs $3.00 input / $15.00 output per million tokens (median across 3 API providers). 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 Medium 3.5 (1.5× as much) and $6.00 for Claude Sonnet 3.7 (2.9× as much).

Which scores higher on benchmarks?

Mistral Medium 3.5 scores higher on the Capabilities Index (ECI): Mistral Medium 3.5 141.6 (#107 of 158), Claude Sonnet 3.7 141.1 (#110 of 158) and DeepSeek-R1 138.6 (#118 of 158). The confidence ranges of the top two overlap (138.4–144.7 vs 139.4–142.6), so treat the gap as small.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-R1 and Mistral Medium 3.5 yet, so there is no like-for-like coding score. On overall capability, Mistral Medium 3.5 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 Medium 3.5 has the largest context window at 262,144 tokens, against 200,000 for Claude Sonnet 3.7 and 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, Mistral Medium 3.5 up to 262,144, Claude Sonnet 3.7 up to 64,000 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-R1 accepts text; Mistral Medium 3.5 accepts text and images; Claude Sonnet 3.7 accepts text, images and PDFs. Claude Sonnet 3.7 handles the widest range of inputs.

Are any of these open source?

DeepSeek-R1 and Mistral Medium 3.5 publishes its weights and can be self-hosted; Claude Sonnet 3.7 is proprietary.

Which is newer?

Mistral Medium 3.5 is the newest, released Apr 29, 2026. Claude Sonnet 3.7 came out Feb 19, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, Claude Sonnet 3.7 Oct 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.