ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek-R1 vs GPT-4.1 vs Llama 4 Maverick 17B Instruct

GPT-4.1 comes out ahead, 65 to 59 and 56 on our weighted score, though Llama 4 Maverick 17B Instruct is 8.4× cheaper per token.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek-R1

    Released Jan 20, 2025

    56/100
    • ECI138.6
    • Price$1.02 / $5.14
    • Context128K
  2. Our pick

    OpenAI

    GPT-4.1

    Released Apr 14, 2025

    65/100
    • ECI136.2
    • Price$2.00 / $8.00
    • Context1.05M
  3. Meta

    Llama 4 Maverick 17B Instruct

    Released Apr 5, 2025

    59/100
    • ECI132.2
    • Price$0.27 / $0.86
    • Context1M
01 — Verdict

GPT-4.1 is our pick

GPT-4.1 is the better all-round choice, scoring 65/100 against Llama 4 Maverick 17B Instruct (59) and DeepSeek-R1 (56). It leads on inputs & features. DeepSeek-R1 wins on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityDeepSeek-R1Capabilities Index (ECI): DeepSeek-R1 138.6 · GPT-4.1 136.2 · Llama 4 Maverick 17B Instruct 132.2
  • Lowest priceLlama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct $0.417 · DeepSeek-R1 $2.05 · GPT-4.1 $3.50 per 1M tokens (3:1 blend)
  • Longest contextGPT-4.1GPT-4.1 1,047,576 · Llama 4 Maverick 17B Instruct 1,000,000 · DeepSeek-R1 128,000 tokens
  • Widest inputsGPT-4.1DeepSeek-R1: Text · GPT-4.1: Text, Images, PDFs · Llama 4 Maverick 17B Instruct: Text, Images
  • Self-hostingDeepSeek-R1 and Llama 4 Maverick 17B InstructPublishes downloadable weights
How the score is built
MeasureWeightDeepSeek-R1GPT-4.1Llama 4 Maverick 17B Instruct
CapabilityCapabilities Index (ECI)67%676461
Inputs & features20%357050
Context window13%326564
Overall100%56/10065/10059/100
02 — Side by side

Every spec in one table

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

DeepSeek-R1 vs GPT-4.1 vs Llama 4 Maverick 17B Instruct specifications side by side
SpecificationDeepSeek-R1DeepSeekGPT-4.1OpenAILlama 4 Maverick 17B InstructMeta
Capability
Capabilities Index (ECI)138.6 (best)136.2132.2
ECI rank#118 of 158 (best)#123 of 158#134 of 158
GPQA DiamondGraduate-level science questions71.7% (best)66.9%67.0%
FrontierMath Tiers 1–3Research-level mathematics—6.0%—
OTIS Mock AIME 2024–2025Competition mathematics53.3% (best)38.3%20.6%
SWE-bench VerifiedFixing real GitHub issues—48.5%—
SimpleQA VerifiedShort factual questions—31.1%—
Price per million tokens
Input$1.02$2.00$0.27 (best)
Output$5.14$8.00$0.86 (best)
Cached input—$0.50—
Blended (3:1)$2.05$3.50$0.417 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 12 providersOfficial OpenAI APIMedian of 16 providers
Limits
Context window128,000 tokens1,047,576 tokens (best)1,000,000 tokens
Max output32,768 tokens (best)32,768 tokens (best)16,384 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesNoNo
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenProprietaryOpen
API model ID—gpt-4.1—
API providers1332 (best)16
ReleasedJan 20, 2025Apr 14, 2025Apr 5, 2025
Knowledge cutoffJul 2024Apr 2024Aug 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
  • GPT-4.1$36.00
  • Llama 4 Maverick 17B Instruct$4.42
04 — Questions

Which should you choose?

Which is better: DeepSeek-R1, GPT-4.1 or Llama 4 Maverick 17B Instruct?

GPT-4.1 is the better all-round choice, scoring 65/100 against Llama 4 Maverick 17B Instruct (59) and DeepSeek-R1 (56). It leads on inputs & features. DeepSeek-R1 wins on capability. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek-R1, GPT-4.1 or Llama 4 Maverick 17B Instruct?

Llama 4 Maverick 17B Instruct is cheaper at $0.27 input / $0.86 output per million tokens (median across 16 API providers). DeepSeek-R1 costs $1.02 input / $5.14 output per million tokens (median across 12 API providers); GPT-4.1 costs $2.00 input / $8.00 output per million tokens (official OpenAI API price). 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 $2.05 for DeepSeek-R1 (4.9× as much) and $3.50 for GPT-4.1 (8.4× as much).

Which scores higher on benchmarks?

DeepSeek-R1 scores higher on the Capabilities Index (ECI): DeepSeek-R1 138.6 (#118 of 158), GPT-4.1 136.2 (#123 of 158) and Llama 4 Maverick 17B Instruct 132.2 (#134 of 158). The confidence ranges of the top two overlap (136.7–140.4 vs 134.1–138.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — DeepSeek-R1 71.7%, Llama 4 Maverick 17B Instruct 67.0%, GPT-4.1 66.9%; OTIS Mock AIME 2024–2025 — DeepSeek-R1 53.3%, GPT-4.1 38.3%, Llama 4 Maverick 17B Instruct 20.6%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-R1 and Llama 4 Maverick 17B Instruct yet, so there is no like-for-like coding score. On overall capability, DeepSeek-R1 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 128,000 for DeepSeek-R1. Maximum output per response: DeepSeek-R1 up to 32,768, GPT-4.1 up to 32,768, Llama 4 Maverick 17B Instruct up to 16,384 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-R1 accepts text; GPT-4.1 accepts text, images and PDFs; Llama 4 Maverick 17B Instruct accepts text and images. GPT-4.1 handles the widest range of inputs.

Are any of these open source?

DeepSeek-R1 and Llama 4 Maverick 17B Instruct publishes its weights and can be self-hosted; 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; DeepSeek-R1 came out Jan 20, 2025. Knowledge cutoff: DeepSeek-R1 Jul 2024, GPT-4.1 Apr 2024, Llama 4 Maverick 17B Instruct Aug 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.