ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Sonnet 3.5 v2 vs Command R+ vs GPT-4.1

No independent capability benchmark covers every model here yet. The score uses price, inputs & features and context window.

Price in rating: Included · Exclude price

  1. Anthropic

    Claude Sonnet 3.5 v2

    Released Oct 22, 2024

    33/100
    • ECI133.3
    • Price$2.80 / $14.00
    • Context200K
  2. Cohere

    Command R+

    Released Aug 30, 2024

    26/100
    • ECI—
    • Price$2.50 / $10.00
    • Context128K
  3. OpenAI

    GPT-4.1

    Released Apr 14, 2025

    45/100
    • ECI136.2
    • Price$2.00 / $8.00
    • Context1.05M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (GPT-4.1 45/100, Claude Sonnet 3.5 v2 33/100, Command R+ 26/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceGPT-4.1GPT-4.1 $3.50 · Command R+ $4.38 · 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 · Command R+ 128,000 tokens
  • Widest inputsClaude Sonnet 3.5 v2 and GPT-4.1Claude Sonnet 3.5 v2: Text, Images, PDFs · Command R+: Text · GPT-4.1: Text, Images, PDFs
  • Self-hostingCommand R+Publishes downloadable weights
How the score is built
MeasureWeightClaude Sonnet 3.5 v2Command R+GPT-4.1
Price50%141923
Inputs & features30%603570
Context window20%393265
Specs & price only100%33/10026/10045/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

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

Claude Sonnet 3.5 v2 vs Command R+ vs GPT-4.1 specifications side by side
SpecificationClaude Sonnet 3.5 v2AnthropicCommand R+CohereGPT-4.1OpenAI
Capability
Capabilities Index (ECI)133.3—136.2 (best)
ECI rank#131 of 158—#123 of 158 (best)
GPQA DiamondGraduate-level science questions55.3%—66.9% (best)
FrontierMath Tiers 1–3Research-level mathematics——6.0%
OTIS Mock AIME 2024–2025Competition mathematics8.5%—38.3% (best)
SWE-bench VerifiedFixing real GitHub issues——48.5%
SimpleQA VerifiedShort factual questions——31.1%
Price per million tokens
Input$2.80$2.50$2.00 (best)
Output$14.00$10.00$8.00 (best)
Cached input——$0.50
Blended (3:1)$5.60$4.38$3.50 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 2 providersOfficial Cohere APIOfficial OpenAI API
Limits
Context window200,000 tokens128,000 tokens1,047,576 tokens (best)
Max output8,192 tokens4,000 tokens32,768 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoYes
PDFsYesNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsProprietaryOpenProprietary
API model ID—command-r-plus-08-2024gpt-4.1
API providers3832 (best)
ReleasedOct 22, 2024Aug 30, 2024Apr 14, 2025
Knowledge cutoffApr 30, 2024Jun 1, 2024Apr 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 3.5 v2$56.00
  • Command R+$45.00
  • GPT-4.1$36.00
04 — Questions

Which should you choose?

Which is better: Claude Sonnet 3.5 v2, Command R+ or GPT-4.1?

There is not enough shared capability evidence to name an overall winner. The scores (GPT-4.1 45/100, Claude Sonnet 3.5 v2 33/100, Command R+ 26/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Claude Sonnet 3.5 v2, Command R+ or GPT-4.1?

GPT-4.1 is cheaper at $2.00 input / $8.00 output per million tokens (official OpenAI API price). Command R+ costs $2.50 input / $10.00 output per million tokens (official Cohere 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 $3.50 per million tokens for GPT-4.1 versus $4.38 for Command R+ (1.3× as much) and $5.60 for Claude Sonnet 3.5 v2 (1.6× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Claude Sonnet 3.5 v2 has an ECI of 133.3, Command R+ has not been scored yet and GPT-4.1 has an ECI of 136.2.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Sonnet 3.5 v2 and Command R+ yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. 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 128,000 for Command R+. Maximum output per response: Claude Sonnet 3.5 v2 up to 8,192, Command R+ up to 4,000, GPT-4.1 up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Claude Sonnet 3.5 v2 accepts text, images and PDFs; Command R+ accepts text; GPT-4.1 accepts text, images and PDFs. Claude Sonnet 3.5 v2 handles the widest range of inputs.

Are any of these open source?

Command R+ publishes its weights and can be self-hosted; Claude Sonnet 3.5 v2 and GPT-4.1 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; Command R+ came out Aug 30, 2024. Knowledge cutoff: Claude Sonnet 3.5 v2 Apr 30, 2024, Command R+ Jun 1, 2024, GPT-4.1 Apr 2024.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.