ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Sonnet 3.7 vs Kimi K2 Instruct vs DeepSeek-R1

Too close to call on our weighted score (Kimi K2 Instruct 53, Claude Sonnet 3.7 52, DeepSeek-R1 50). The right pick depends on what you value most.

Price in rating: Included · Exclude price

  1. Anthropic

    Claude Sonnet 3.7

    Released Feb 19, 2025

    52/100
    • ECI141.1
    • Price$3.00 / $15.00
    • Context200K
  2. Moonshot AI

    Kimi K2 Instruct

    Released Jul 11, 2025

    53/100
    • ECI141.3
    • Price$0.57 / $2.30
    • Context131K
  3. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    50/100
    • ECI138.6
    • Price$1.02 / $5.14
    • Context128K
01 — Verdict

Too close to call

It is close. Our weighted score puts them within 2 points (Kimi K2 Instruct 53/100, Claude Sonnet 3.7 52/100, DeepSeek-R1 50/100), so choose by what matters most for your work: Kimi K2 Instruct for raw capability and Claude Sonnet 3.7 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityKimi K2 InstructCapabilities Index (ECI): Kimi K2 Instruct 141.3 · Claude Sonnet 3.7 141.1 · DeepSeek-R1 138.6
  • Lowest priceKimi K2 InstructKimi K2 Instruct $1.00 · DeepSeek-R1 $2.05 · Claude Sonnet 3.7 $6.00 per 1M tokens (3:1 blend)
  • Longest contextClaude Sonnet 3.7Claude Sonnet 3.7 200,000 · Kimi K2 Instruct 131,072 · DeepSeek-R1 128,000 tokens
  • Widest inputsClaude Sonnet 3.7Claude Sonnet 3.7: Text, Images, PDFs · Kimi K2 Instruct: Text · DeepSeek-R1: Text
  • Self-hostingKimi K2 Instruct and DeepSeek-R1Publishes downloadable weights (Modified MIT)
How the score is built
MeasureWeightClaude Sonnet 3.7Kimi K2 InstructDeepSeek-R1
CapabilityCapabilities Index (ECI)50%696967
Price25%124834
Inputs & features15%702535
Context window10%393232
Overall100%52/10053/10050/100
02 — Side by side

Every spec in one table

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

Claude Sonnet 3.7 vs Kimi K2 Instruct vs DeepSeek-R1 specifications side by side
SpecificationClaude Sonnet 3.7AnthropicKimi K2 InstructMoonshot AIDeepSeek-R1DeepSeek
Capability
Capabilities Index (ECI)141.1141.3 (best)138.6
ECI rank#110 of 158#108 of 158 (best)#118 of 158
GPQA DiamondGraduate-level science questions79.7% (best)—71.7%
OTIS Mock AIME 2024–2025Competition mathematics57.8% (best)—53.3%
SWE-bench VerifiedFixing real GitHub issues61.0%——
Price per million tokens
Input$3.00$0.57 (best)$1.02
Output$15.00$2.30 (best)$5.14
Cached input———
Blended (3:1)$6.00$1.00 (best)$2.05
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersMedian of 11 providersMedian of 12 providers
Limits
Context window200,000 tokens (best)131,072 tokens128,000 tokens
Max output64,000 tokens (best)32,768 tokens32,768 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoYes
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsProprietaryOpenModified MITOpen
API model ID———
API providers41113 (best)
ReleasedFeb 19, 2025Jul 11, 2025Jan 20, 2025
Knowledge cutoffOct 31, 2024—Jul 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.

  • Claude Sonnet 3.7$60.00
  • Kimi K2 Instruct$10.30
  • DeepSeek-R1$20.53
04 — Questions

Which should you choose?

Which is better: Claude Sonnet 3.7, Kimi K2 Instruct or DeepSeek-R1?

It is close. Our weighted score puts them within 2 points (Kimi K2 Instruct 53/100, Claude Sonnet 3.7 52/100, DeepSeek-R1 50/100), so choose by what matters most for your work: Kimi K2 Instruct for raw capability and Claude Sonnet 3.7 for long inputs. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Sonnet 3.7, Kimi K2 Instruct or DeepSeek-R1?

Kimi K2 Instruct is cheaper at $0.57 input / $2.30 output per million tokens (median across 11 API providers). DeepSeek-R1 costs $1.02 input / $5.14 output per million tokens (median across 12 API providers); 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 $1.00 per million tokens for Kimi K2 Instruct versus $2.05 for DeepSeek-R1 (2× as much) and $6.00 for Claude Sonnet 3.7 (6× as much).

Which scores higher on benchmarks?

Kimi K2 Instruct scores higher on the Capabilities Index (ECI): Kimi K2 Instruct 141.3 (#108 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 (138.3–144.0 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 Kimi K2 Instruct and DeepSeek-R1 yet, so there is no like-for-like coding score. On overall capability, Kimi K2 Instruct 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 3.7 has the largest context window at 200,000 tokens, against 131,072 for Kimi K2 Instruct and 128,000 for DeepSeek-R1. Maximum output per response: Claude Sonnet 3.7 up to 64,000, Kimi K2 Instruct up to 32,768, DeepSeek-R1 up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Claude Sonnet 3.7 accepts text, images and PDFs; Kimi K2 Instruct accepts text; DeepSeek-R1 accepts text. Claude Sonnet 3.7 handles the widest range of inputs.

Are any of these open source?

Kimi K2 Instruct and DeepSeek-R1 publishes its weights (Modified MIT) and can be self-hosted; Claude Sonnet 3.7 is proprietary.

Which is newer?

Kimi K2 Instruct is the newest, released Jul 11, 2025. Claude Sonnet 3.7 came out Feb 19, 2025; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: Claude Sonnet 3.7 Oct 31, 2024, DeepSeek-R1 Jul 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.