ZMIME
Comparison · 3 models · Updated Nov 18, 2026

DeepSeek R1 0528 vs Grok Build 0.1 vs Qwen3.5 122B-A10B

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

Price in rating: Excluded · Include price

  1. DeepSeek

    DeepSeek R1 0528

    Released May 28, 2025

    35/100
    • ECI140.8
    • Price$0.512 / $2.19
    • Context164K
  2. xAI

    Grok Build 0.1

    Released Apr 16, 2026

    65/100
    • ECI—
    • Price$1.00 / $2.00
    • Context256K
  3. Alibaba (Qwen)

    Qwen3.5 122B-A10B

    Released Feb 23, 2026

    65/100
    • ECI—
    • Price$0.40 / $3.20
    • Context262K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 122B-A10B 65/100, Grok Build 0.1 65/100, DeepSeek R1 0528 35/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. 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 priceDeepSeek R1 0528DeepSeek R1 0528 $0.932 · Qwen3.5 122B-A10B $1.10 · Grok Build 0.1 $1.25 per 1M tokens (3:1 blend)
  • Longest contextQwen3.5 122B-A10BQwen3.5 122B-A10B 262,144 · Grok Build 0.1 256,000 · DeepSeek R1 0528 163,840 tokens
  • Widest inputsGrok Build 0.1 and Qwen3.5 122B-A10BDeepSeek R1 0528: Text · Grok Build 0.1: Text, Images, PDFs · Qwen3.5 122B-A10B: Text, Images, Video
  • Self-hostingDeepSeek R1 0528 and Qwen3.5 122B-A10BPublishes downloadable weights (MIT)
How the score is built
MeasureWeightDeepSeek R1 0528Grok Build 0.1Qwen3.5 122B-A10B
Inputs & features60%358080
Context window40%364343
Specs only100%35/10065/10065/100

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.

DeepSeek R1 0528 vs Grok Build 0.1 vs Qwen3.5 122B-A10B specifications side by side
SpecificationDeepSeek R1 0528DeepSeekGrok Build 0.1xAIQwen3.5 122B-A10BAlibaba (Qwen)
Capability
Capabilities Index (ECI)140.8——
ECI rank#113 of 158——
GPQA DiamondGraduate-level science questions76.3%——
OTIS Mock AIME 2024–2025Competition mathematics66.4%——
Price per million tokens
Input$0.512$1.00$0.40 (best)
Output$2.19$2.00 (best)$3.20
Cached input—$0.20—
Blended (3:1)$0.932 (best)$1.25$1.10
Long-context rateSame rateOver 200K: $2.00 / $4.00Same rate
Price sourceMedian of 16 providersOfficial xAI APIOfficial Alibaba API
Limits
Context window163,840 tokens256,000 tokens262,144 tokens (best)
Max output32,768 tokens256,000 tokens (best)65,536 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesNo
AudioNoNoNo
VideoNoNoYes
ReasoningYesYesYes
Tool callingYesYesYes
Structured outputNoYesYes
Availability
WeightsOpenMITProprietaryOpen
API model ID—grok-build-0.1qwen3.5-122b-a10b
API providers161824 (best)
ReleasedMay 28, 2025Apr 16, 2026Feb 23, 2026
Knowledge cutoff———
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
  • Grok Build 0.1$14.00
  • Qwen3.5 122B-A10B$10.40
04 — Questions

Which should you choose?

Which is better: DeepSeek R1 0528, Grok Build 0.1 or Qwen3.5 122B-A10B?

There is not enough shared capability evidence to name an overall winner. The scores (Qwen3.5 122B-A10B 65/100, Grok Build 0.1 65/100, DeepSeek R1 0528 35/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, DeepSeek R1 0528, Grok Build 0.1 or Qwen3.5 122B-A10B?

DeepSeek R1 0528 is cheaper at $0.512 input / $2.19 output per million tokens (median across 16 API providers). Qwen3.5 122B-A10B costs $0.40 input / $3.20 output per million tokens (official Alibaba API price); Grok Build 0.1 costs $1.00 input / $2.00 output per million tokens (official xAI API price). At a typical mix of three input tokens to one output token, that is $0.932 per million tokens for DeepSeek R1 0528 versus $1.10 for Qwen3.5 122B-A10B (1.2× as much) and $1.25 for Grok Build 0.1 (1.3× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. DeepSeek R1 0528 has an ECI of 140.8, Grok Build 0.1 has not been scored yet and Qwen3.5 122B-A10B has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for DeepSeek R1 0528, Grok Build 0.1 and Qwen3.5 122B-A10B 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?

Qwen3.5 122B-A10B has the largest context window at 262,144 tokens, against 256,000 for Grok Build 0.1 and 163,840 for DeepSeek R1 0528. Maximum output per response: DeepSeek R1 0528 up to 32,768, Grok Build 0.1 up to 256,000, Qwen3.5 122B-A10B up to 65,536 tokens.

Which can read images, PDFs, audio or video?

DeepSeek R1 0528 accepts text; Grok Build 0.1 accepts text, images and PDFs; Qwen3.5 122B-A10B accepts text, images and video. Grok Build 0.1 handles the widest range of inputs.

Are any of these open source?

DeepSeek R1 0528 and Qwen3.5 122B-A10B publishes its weights (MIT) and can be self-hosted; Grok Build 0.1 is proprietary.

Which is newer?

Grok Build 0.1 is the newest, released Apr 16, 2026. Qwen3.5 122B-A10B came out Feb 23, 2026; DeepSeek R1 0528 came out May 28, 2025.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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.