ZMIME
Comparison · 3 models · Updated Oct 4, 2026

DeepSeek-V3 vs GPT OSS 120B vs Llama 4 Maverick 17B Instruct

GPT OSS 120B comes out ahead, 61 to 58 and 50 on our weighted score, and it is the cheaper option too.

  1. DeepSeek

    DeepSeek-V3

    Released Dec 26, 2024

    50/100
    • ECI132.3
    • Price$0.32 / $1.10
    • Context131K
    Full specs Remove DeepSeek-V3
  2. Our pick

    OpenAI

    GPT OSS 120B

    Released Aug 5, 2025

    61/100
    • ECI140.0
    • Price$0.15 / $0.60
    • Context131K
    Full specs Remove GPT OSS 120B

  3. Meta

    Llama 4 Maverick 17B Instruct

    Released Apr 5, 2025

    58/100
    • ECI132.2
    • Price$0.321 / $0.91
    • Context1M
    Full specs Remove Llama 4 Maverick 17B Instruct
01 — Verdict

GPT OSS 120B is our pick

GPT OSS 120B is the better all-round choice, scoring 61/100 against Llama 4 Maverick 17B Instruct (58) and DeepSeek-V3 (50). It leads on capability and price. Llama 4 Maverick 17B Instruct wins on inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT OSS 120BCapabilities Index (ECI): GPT OSS 120B 140.0 · DeepSeek-V3 132.3 · Llama 4 Maverick 17B Instruct 132.2
  • Lowest priceGPT OSS 120BGPT OSS 120B $0.263 · Llama 4 Maverick 17B Instruct $0.468 · DeepSeek-V3 $0.515 per 1M tokens (3:1 blend)
  • Longest contextLlama 4 Maverick 17B InstructLlama 4 Maverick 17B Instruct 1,000,000 · DeepSeek-V3 131,072 · GPT OSS 120B 131,072 tokens
  • Widest inputsLlama 4 Maverick 17B InstructDeepSeek-V3: Text · GPT OSS 120B: Text · Llama 4 Maverick 17B Instruct: Text, Images
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightDeepSeek-V3GPT OSS 120BLlama 4 Maverick 17B Instruct
CapabilityCapabilities Index (ECI)50%566556
Price25%647766
Inputs & features15%254550
Context window10%242460
Overall100%50/10061/10058/100
02 — Side by side

Every spec in one table

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

DeepSeek-V3 vs GPT OSS 120B vs Llama 4 Maverick 17B Instruct specifications side by side
SpecificationDeepSeek-V3DeepSeekGPT OSS 120BOpenAILlama 4 Maverick 17B InstructMeta
Capability
Capabilities Index (ECI)132.3140.0 (best)132.2
ECI rank#121 of 148#99 of 148 (best)#122 of 148
GPQA DiamondGraduate-level science questions56.5%75.8% (best)67.0%
OTIS Mock AIME 2024–2025Competition mathematics15.8%88.9% (best)20.6%
Price per million tokens
Input$0.32$0.15 (best)$0.321
Output$1.10$0.60 (best)$0.91
Cached input———
Blended (3:1)$0.515$0.263 (best)$0.468
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 5 providersMedian of 36 providersMedian of 6 providers
Limits
Context window131,072 tokens131,072 tokens1,000,000 tokens (best)
Max output8,192 tokens32,768 tokens (best)16,384 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesNo
Tool callingYesYesYes
Structured outputNoYesNo
Availability
WeightsOpenDeepSeek Model LicenseOpenOpen
API model ID———
API providers539 (best)6
ReleasedDec 26, 2024Aug 5, 2025Apr 5, 2025
Knowledge cutoff——Aug 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-V3$5.40
  • GPT OSS 120B$2.70
  • Llama 4 Maverick 17B Instruct$5.03
04 — Questions

Which should you choose?

Which is better: DeepSeek-V3, GPT OSS 120B or Llama 4 Maverick 17B Instruct?

GPT OSS 120B is the better all-round choice, scoring 61/100 against Llama 4 Maverick 17B Instruct (58) and DeepSeek-V3 (50). It leads on capability and price. Llama 4 Maverick 17B Instruct wins on inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, DeepSeek-V3, GPT OSS 120B or Llama 4 Maverick 17B Instruct?

GPT OSS 120B is cheaper at $0.15 input / $0.60 output per million tokens (median across 36 API providers). Llama 4 Maverick 17B Instruct costs $0.321 input / $0.91 output per million tokens (median across 6 API providers); DeepSeek-V3 costs $0.32 input / $1.10 output per million tokens (median across 5 API providers). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for GPT OSS 120B versus $0.468 for Llama 4 Maverick 17B Instruct (1.8× as much) and $0.515 for DeepSeek-V3 (2× as much).

Which scores higher on benchmarks?

GPT OSS 120B scores higher on the Capabilities Index (ECI): GPT OSS 120B 140.0 (#99 of 148), DeepSeek-V3 132.3 (#121 of 148) and Llama 4 Maverick 17B Instruct 132.2 (#122 of 148). The confidence ranges of the top two overlap (135.3–142.3 vs 127.5–135.5), so treat the gap as small. On individual benchmarks: GPQA Diamond — GPT OSS 120B 75.8%, Llama 4 Maverick 17B Instruct 67.0%, DeepSeek-V3 56.5%; OTIS Mock AIME 2024–2025 — GPT OSS 120B 88.9%, Llama 4 Maverick 17B Instruct 20.6%, DeepSeek-V3 15.8%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek-V3, GPT OSS 120B and Llama 4 Maverick 17B Instruct yet, so there is no like-for-like coding score. On overall capability, GPT OSS 120B 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?

Llama 4 Maverick 17B Instruct has the largest context window at 1,000,000 tokens, against 131,072 for DeepSeek-V3 and 131,072 for GPT OSS 120B. Maximum output per response: DeepSeek-V3 up to 8,192, GPT OSS 120B up to 32,768, Llama 4 Maverick 17B Instruct up to 16,384 tokens.

Which can read images, PDFs, audio or video?

DeepSeek-V3 accepts text; GPT OSS 120B accepts text; Llama 4 Maverick 17B Instruct accepts text and images. Llama 4 Maverick 17B Instruct handles the widest range of inputs.

Are any of these open source?

Yes, all three publish their weights (DeepSeek Model License), so you can self-host them.

Which is newer?

GPT OSS 120B is the newest, released Aug 5, 2025. Llama 4 Maverick 17B Instruct came out Apr 5, 2025; DeepSeek-V3 came out Dec 26, 2024. Knowledge cutoff: Llama 4 Maverick 17B Instruct Aug 2024.

How do you decide the winner?

Each model gets a 0–100 score on 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 Oct 4, 2026.

05 — Keep comparing

Related comparisons