ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Baichuan M2 32B vs DeepSeek R1 0528 Qwen3 8B vs DeepSeek V4 Pro 0813

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

Price in rating: Excluded · Include price

  1. Baichuan

    Baichuan M2 32B

    Released Aug 13, 2025

    19/100
    • ECI—
    • Price$0.07 / $0.07
    • Context131K
  2. DeepSeek

    DeepSeek R1 0528 Qwen3 8B

    Released May 29, 2025

    19/100
    • ECI—
    • Price$0.06 / $0.09
    • Context131K
  3. DeepSeek

    DeepSeek V4 Pro 0813

    Released Aug 13, 2026

    53/100
    • ECI156.0
    • Price$0.66 / $1.98
    • Context1M
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (DeepSeek V4 Pro 0813 53/100, Baichuan M2 32B 19/100, DeepSeek R1 0528 Qwen3 8B 19/100) 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 0528 Qwen3 8BDeepSeek R1 0528 Qwen3 8B $0.068 · Baichuan M2 32B $0.07 · DeepSeek V4 Pro 0813 $0.99 per 1M tokens (3:1 blend)
  • Longest contextDeepSeek V4 Pro 0813DeepSeek V4 Pro 0813 1,000,000 · Baichuan M2 32B 131,072 · DeepSeek R1 0528 Qwen3 8B 131,072 tokens
  • Widest inputsSame inputsBaichuan M2 32B: Text · DeepSeek R1 0528 Qwen3 8B: Text · DeepSeek V4 Pro 0813: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightBaichuan M2 32BDeepSeek R1 0528 Qwen3 8BDeepSeek V4 Pro 0813
Inputs & features60%101045
Context window40%323264
Specs only100%19/10019/10053/100

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.

Baichuan M2 32B vs DeepSeek R1 0528 Qwen3 8B vs DeepSeek V4 Pro 0813 specifications side by side
SpecificationBaichuan M2 32BBaichuanDeepSeek R1 0528 Qwen3 8BDeepSeekDeepSeek V4 Pro 0813DeepSeek
Capability
Capabilities Index (ECI)——156.0
ECI rank——#42 of 158
GPQA DiamondGraduate-level science questions—9.3%91.7% (best)
FrontierMath Tiers 1–3Research-level mathematics——64.6%
OTIS Mock AIME 2024–2025Competition mathematics—43.9%98.6% (best)
SimpleQA VerifiedShort factual questions——52.9%
Price per million tokens
Input$0.07$0.06 (best)$0.66
Output$0.07 (best)$0.09$1.98
Cached input——$0.022
Blended (3:1)$0.07$0.068 (best)$0.99
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 1 providersMedian of 1 providersOfficial DeepSeek API
Limits
Context window131,072 tokens131,072 tokens1,000,000 tokens (best)
Max output131,072 tokens32,000 tokens384,000 tokens (best)
Inputs and features
TextYesYesYes
ImagesNoNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesYeslow · high · max
Tool callingNoNoYes
Structured outputNoNoYes
Availability
WeightsOpenApache-2.0OpenMITOpenMIT
API model ID——deepseek-v4-pro
API providers1154 (best)
ReleasedAug 13, 2025May 29, 2025Aug 13, 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.

  • Baichuan M2 32B$0.84
  • DeepSeek R1 0528 Qwen3 8B$0.78
  • DeepSeek V4 Pro 0813$10.56
04 — Questions

Which should you choose?

Which is better: Baichuan M2 32B, DeepSeek R1 0528 Qwen3 8B or DeepSeek V4 Pro 0813?

There is not enough shared capability evidence to name an overall winner. The scores (DeepSeek V4 Pro 0813 53/100, Baichuan M2 32B 19/100, DeepSeek R1 0528 Qwen3 8B 19/100) 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, Baichuan M2 32B, DeepSeek R1 0528 Qwen3 8B or DeepSeek V4 Pro 0813?

DeepSeek R1 0528 Qwen3 8B is cheaper at $0.06 input / $0.09 output per million tokens (median across 1 API provider). Baichuan M2 32B costs $0.07 input / $0.07 output per million tokens (median across 1 API provider); DeepSeek V4 Pro 0813 costs $0.66 input / $1.98 output per million tokens (official DeepSeek API price). At a typical mix of three input tokens to one output token, that is $0.068 per million tokens for DeepSeek R1 0528 Qwen3 8B versus $0.07 for Baichuan M2 32B (1× as much) and $0.99 for DeepSeek V4 Pro 0813 (15× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Baichuan M2 32B has not been scored yet, DeepSeek R1 0528 Qwen3 8B has not been scored yet and DeepSeek V4 Pro 0813 has an ECI of 156.0.

Which is better for coding?

There are no published SWE-bench Verified results for Baichuan M2 32B, DeepSeek R1 0528 Qwen3 8B and DeepSeek V4 Pro 0813 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Baichuan M2 32B and DeepSeek R1 0528 Qwen3 8B does not support tool calling, which most coding agents need.

Which has the bigger context window?

DeepSeek V4 Pro 0813 has the largest context window at 1,000,000 tokens, against 131,072 for Baichuan M2 32B and 131,072 for DeepSeek R1 0528 Qwen3 8B. Maximum output per response: Baichuan M2 32B up to 131,072, DeepSeek R1 0528 Qwen3 8B up to 32,000, DeepSeek V4 Pro 0813 up to 384,000 tokens.

Which can read images, PDFs, audio or video?

Baichuan M2 32B accepts text; DeepSeek R1 0528 Qwen3 8B accepts text; DeepSeek V4 Pro 0813 accepts text. They handle the same number of input types.

Are any of these open source?

Yes, all three publish their weights (Apache-2.0 and MIT), so you can self-host them.

Which is newer?

DeepSeek V4 Pro 0813 is the newest, released Aug 13, 2026. Baichuan M2 32B came out Aug 13, 2025; DeepSeek R1 0528 Qwen3 8B came out May 29, 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.