ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek R1 0528 vs Nemotron 3 Ultra 550B A55B vs Qwen3.5 Plus

Qwen3.5 Plus comes out ahead, 74 to 67 and 57 on our weighted score, and it is the cheaper option too.

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek R1 0528

    Released May 28, 2025

    57/100
    • ECI140.8
    • Price$0.512 / $2.19
    • Context164K
  2. NVIDIA

    Nemotron 3 Ultra 550B A55B

    Released Jun 4, 2026

    67/100
    • ECI147.0
    • Price$0.55 / $2.40
    • Context1M
  3. Our pick

    Alibaba (Qwen)

    Qwen3.5 Plus

    Released Feb 16, 2026

    74/100
    • ECI147.3
    • Price$0.40 / $2.40
    • Context1M
01 — Verdict

Qwen3.5 Plus is our pick

Qwen3.5 Plus is the better all-round choice, scoring 74/100 against Nemotron 3 Ultra 550B A55B (67) and DeepSeek R1 0528 (57). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

  • CapabilityQwen3.5 PlusCapabilities Index (ECI): Qwen3.5 Plus 147.3 · Nemotron 3 Ultra 550B A55B 147.0 · DeepSeek R1 0528 140.8
  • Lowest priceQwen3.5 PlusQwen3.5 Plus $0.90 · DeepSeek R1 0528 $0.932 · Nemotron 3 Ultra 550B A55B $1.01 per 1M tokens (3:1 blend)
  • Longest contextNemotron 3 Ultra 550B A55B and Qwen3.5 PlusNemotron 3 Ultra 550B A55B 1,000,000 · Qwen3.5 Plus 1,000,000 · DeepSeek R1 0528 163,840 tokens
  • Widest inputsQwen3.5 PlusDeepSeek R1 0528: Text · Nemotron 3 Ultra 550B A55B: Text · Qwen3.5 Plus: Text, Images, Video
  • Self-hostingDeepSeek R1 0528 and Nemotron 3 Ultra 550B A55BPublishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek R1 0528Nemotron 3 Ultra 550B A55BQwen3.5 Plus
CapabilityCapabilities Index (ECI)67%697475
Inputs & features20%354580
Context window13%366464
Overall100%57/10067/10074/100
02 — Side by side

Every spec in one table

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

DeepSeek R1 0528 vs Nemotron 3 Ultra 550B A55B vs Qwen3.5 Plus specifications side by side
SpecificationDeepSeek R1 0528DeepSeekNemotron 3 Ultra 550B A55BNVIDIAQwen3.5 PlusAlibaba (Qwen)
Capability
Capabilities Index (ECI)140.8147.0147.3 (best)
ECI rank#113 of 158#82 of 158#80 of 158 (best)
GPQA DiamondGraduate-level science questions76.3%85.4% (best)84.9%
OTIS Mock AIME 2024–2025Competition mathematics66.4%86.7% (best)86.7% (best)
SimpleQA VerifiedShort factual questions——25.4%
Price per million tokens
Input$0.512$0.55$0.40 (best)
Output$2.19 (best)$2.40$2.40
Cached input———
Blended (3:1)$0.932$1.01$0.90 (best)
Long-context rateSame rateSame rateOver 256K: $0.50 / $3.00
Price sourceMedian of 16 providersMedian of 20 providersOfficial Alibaba API
Limits
Context window163,840 tokens1,000,000 tokens (best)1,000,000 tokens (best)
Max output32,768 tokens128,000 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesmedium · highYes
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsOpenMITOpenProprietary
API model ID—nvidia/nemotron-3-ultra-550b-a55bqwen3.5-plus
API providers1626 (best)14
ReleasedMay 28, 2025Jun 4, 2026Feb 16, 2026
Knowledge cutoff—Sep 2025Apr 2025
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 0528$9.50
  • Nemotron 3 Ultra 550B A55B$10.30
  • Qwen3.5 Plus$8.80
04 — Questions

Which should you choose?

Which is better: DeepSeek R1 0528, Nemotron 3 Ultra 550B A55B or Qwen3.5 Plus?

Qwen3.5 Plus is the better all-round choice, scoring 74/100 against Nemotron 3 Ultra 550B A55B (67) and DeepSeek R1 0528 (57). It leads on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.

Which is cheaper, DeepSeek R1 0528, Nemotron 3 Ultra 550B A55B or Qwen3.5 Plus?

Qwen3.5 Plus is cheaper at $0.40 input / $2.40 output per million tokens (official Alibaba API price). DeepSeek R1 0528 costs $0.512 input / $2.19 output per million tokens (median across 16 API providers); Nemotron 3 Ultra 550B A55B costs $0.55 input / $2.40 output per million tokens (median across 20 API providers; free on Nvidia). At a typical mix of three input tokens to one output token, that is $0.90 per million tokens for Qwen3.5 Plus versus $0.932 for DeepSeek R1 0528 (1× as much) and $1.01 for Nemotron 3 Ultra 550B A55B (1.1× as much).

Which scores higher on benchmarks?

Qwen3.5 Plus scores higher on the Capabilities Index (ECI): Qwen3.5 Plus 147.3 (#80 of 158), Nemotron 3 Ultra 550B A55B 147.0 (#82 of 158) and DeepSeek R1 0528 140.8 (#113 of 158). The confidence ranges of the top two overlap (145.4–149.2 vs 145.0–149.1), so treat the gap as small. On individual benchmarks: GPQA Diamond — Nemotron 3 Ultra 550B A55B 85.4%, Qwen3.5 Plus 84.9%, DeepSeek R1 0528 76.3%; OTIS Mock AIME 2024–2025 — Nemotron 3 Ultra 550B A55B 86.7%, Qwen3.5 Plus 86.7%, DeepSeek R1 0528 66.4%.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek R1 0528, Nemotron 3 Ultra 550B A55B and Qwen3.5 Plus yet, so there is no like-for-like coding score. On overall capability, Qwen3.5 Plus 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?

Nemotron 3 Ultra 550B A55B and Qwen3.5 Plus have the largest context windows (1,000,000 and 1,000,000 tokens), against 163,840 for DeepSeek R1 0528. Maximum output per response: DeepSeek R1 0528 up to 32,768, Nemotron 3 Ultra 550B A55B up to 128,000, Qwen3.5 Plus up to 65,536 tokens.

Which can read images, PDFs, audio or video?

DeepSeek R1 0528 accepts text; Nemotron 3 Ultra 550B A55B accepts text; Qwen3.5 Plus accepts text, images and video. Qwen3.5 Plus handles the widest range of inputs.

Are any of these open source?

DeepSeek R1 0528 and Nemotron 3 Ultra 550B A55B publishes its weights (MIT) and can be self-hosted; Qwen3.5 Plus is proprietary.

Which is newer?

Nemotron 3 Ultra 550B A55B is the newest, released Jun 4, 2026. Qwen3.5 Plus came out Feb 16, 2026; DeepSeek R1 0528 came out May 28, 2025. Knowledge cutoff: Nemotron 3 Ultra 550B A55B Sep 2025, Qwen3.5 Plus Apr 2025.

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.