ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Sonnet 3.5 v2 vs Llama 4 Maverick 17B Instruct vs GPT-4.1

Llama 4 Maverick 17B Instruct comes out ahead, 60 to 55 and 47 on our weighted score, and it is the cheaper option too.

Price in rating: Included · Exclude price

  1. Anthropic

    Claude Sonnet 3.5 v2

    Released Oct 22, 2024

    47/100
    • ECI133.3
    • Price$2.80 / $14.00
    • Context200K
  2. Our pick

    Meta

    Llama 4 Maverick 17B Instruct

    Released Apr 5, 2025

    60/100
    • ECI132.2
    • Price$0.27 / $0.86
    • Context1M
  3. OpenAI

    GPT-4.1

    Released Apr 14, 2025

    55/100
    • ECI136.2
    • Price$2.00 / $8.00
    • Context1.05M
01 — Verdict

Llama 4 Maverick 17B Instruct is our pick

Llama 4 Maverick 17B Instruct is the better all-round choice, scoring 60/100 against GPT-4.1 (55) and Claude Sonnet 3.5 v2 (47). It leads on price. GPT-4.1 wins on capability and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT-4.1Capabilities Index (ECI): GPT-4.1 136.2 · Claude Sonnet 3.5 v2 133.3 · Llama 4 Maverick 17B Instruct 132.2
  • Lowest priceLlama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct $0.417 · 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 · Llama 4 Maverick 17B Instruct 1,000,000 · Claude Sonnet 3.5 v2 200,000 tokens
  • Widest inputsClaude Sonnet 3.5 v2 and GPT-4.1Claude Sonnet 3.5 v2: Text, Images, PDFs · Llama 4 Maverick 17B Instruct: Text, Images · GPT-4.1: Text, Images, PDFs
  • Self-hostingLlama 4 Maverick 17B InstructPublishes downloadable weights
How the score is built
MeasureWeightClaude Sonnet 3.5 v2Llama 4 Maverick 17B InstructGPT-4.1
CapabilityCapabilities Index (ECI)50%626164
Price25%146523
Inputs & features15%605070
Context window10%396465
Overall100%47/10060/10055/100
02 — Side by side

Every spec in one table

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

Claude Sonnet 3.5 v2 vs Llama 4 Maverick 17B Instruct vs GPT-4.1 specifications side by side
SpecificationClaude Sonnet 3.5 v2AnthropicLlama 4 Maverick 17B InstructMetaGPT-4.1OpenAI
Capability
Capabilities Index (ECI)133.3132.2136.2 (best)
ECI rank#131 of 158#134 of 158#123 of 158 (best)
GPQA DiamondGraduate-level science questions55.3%67.0% (best)66.9%
FrontierMath Tiers 1–3Research-level mathematics——6.0%
OTIS Mock AIME 2024–2025Competition mathematics8.5%20.6%38.3% (best)
SWE-bench VerifiedFixing real GitHub issues——48.5%
SimpleQA VerifiedShort factual questions——31.1%
Price per million tokens
Input$2.80$0.27 (best)$2.00
Output$14.00$0.86 (best)$8.00
Cached input——$0.50
Blended (3:1)$5.60$0.417 (best)$3.50
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 2 providersMedian of 16 providersOfficial OpenAI API
Limits
Context window200,000 tokens1,000,000 tokens1,047,576 tokens (best)
Max output8,192 tokens16,384 tokens32,768 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoYes
Availability
WeightsProprietaryOpenProprietary
API model ID——gpt-4.1
API providers31632 (best)
ReleasedOct 22, 2024Apr 5, 2025Apr 14, 2025
Knowledge cutoffApr 30, 2024Aug 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
  • Llama 4 Maverick 17B Instruct$4.42
  • GPT-4.1$36.00
04 — Questions

Which should you choose?

Which is better: Claude Sonnet 3.5 v2, Llama 4 Maverick 17B Instruct or GPT-4.1?

Llama 4 Maverick 17B Instruct is the better all-round choice, scoring 60/100 against GPT-4.1 (55) and Claude Sonnet 3.5 v2 (47). It leads on price. GPT-4.1 wins on capability and inputs & features. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Sonnet 3.5 v2, Llama 4 Maverick 17B Instruct or GPT-4.1?

Llama 4 Maverick 17B Instruct is cheaper at $0.27 input / $0.86 output per million tokens (median across 16 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 $0.417 per million tokens for Llama 4 Maverick 17B Instruct versus $3.50 for GPT-4.1 (8.4× as much) and $5.60 for Claude Sonnet 3.5 v2 (13× 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 Llama 4 Maverick 17B Instruct 132.2 (#134 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 — Llama 4 Maverick 17B Instruct 67.0%, GPT-4.1 66.9%, Claude Sonnet 3.5 v2 55.3%; OTIS Mock AIME 2024–2025 — GPT-4.1 38.3%, Llama 4 Maverick 17B Instruct 20.6%, Claude Sonnet 3.5 v2 8.5%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Sonnet 3.5 v2 and Llama 4 Maverick 17B Instruct 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 1,000,000 for Llama 4 Maverick 17B Instruct and 200,000 for Claude Sonnet 3.5 v2. Maximum output per response: Claude Sonnet 3.5 v2 up to 8,192, Llama 4 Maverick 17B Instruct up to 16,384, 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; Llama 4 Maverick 17B Instruct accepts text and images; 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?

Llama 4 Maverick 17B Instruct 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. Llama 4 Maverick 17B Instruct came out Apr 5, 2025; Claude Sonnet 3.5 v2 came out Oct 22, 2024. Knowledge cutoff: Claude Sonnet 3.5 v2 Apr 30, 2024, Llama 4 Maverick 17B Instruct Aug 2024, GPT-4.1 Apr 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.