ZMIME
Comparison · 3 models · Updated Nov 2, 2026

GPT OSS 20B vs ERNIE 4.5 VL 424B A47B vs Qwen3 30B-A3B Instruct 2507

GPT OSS 20B comes out ahead, 61 to 57 and 44 on our weighted score, and it is the cheaper option too.

  1. Our pick

    OpenAI

    GPT OSS 20B

    Released Aug 5, 2025

    61/100
    • ECI137.8
    • Price$0.07 / $0.25
    • Context131K
    Full specs Remove GPT OSS 20B

  2. Baidu

    ERNIE 4.5 VL 424B A47B

    Released Jun 30, 2025

    44/100
    • ECI—
    • Price$0.42 / $1.25
    • Context123K
    Full specs Remove ERNIE 4.5 VL 424B A47B

  3. Alibaba (Qwen)

    Qwen3 30B-A3B Instruct 2507

    Released Jul 28, 2025

    57/100
    • ECI137.3
    • Price$0.10 / $0.30
    • Context262K
    Full specs Remove Qwen3 30B-A3B Instruct 2507
01 — Verdict

GPT OSS 20B is our pick

GPT OSS 20B is the better all-round choice, scoring 61/100 against Qwen3 30B-A3B Instruct 2507 (57) and ERNIE 4.5 VL 424B A47B (44). It leads on price. Qwen3 30B-A3B Instruct 2507 wins on context window. The score weighs price 50%, inputs & features 30%, context window 20%. 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 priceGPT OSS 20BGPT OSS 20B $0.115 · Qwen3 30B-A3B Instruct 2507 $0.15 · ERNIE 4.5 VL 424B A47B $0.627 per 1M tokens (3:1 blend)
  • Longest contextQwen3 30B-A3B Instruct 2507Qwen3 30B-A3B Instruct 2507 262,144 · GPT OSS 20B 131,072 · ERNIE 4.5 VL 424B A47B 123,000 tokens
  • Widest inputsERNIE 4.5 VL 424B A47B GPT OSS 20B: Text · ERNIE 4.5 VL 424B A47B : Text, Images · Qwen3 30B-A3B Instruct 2507: Text
  • Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
How the score is built
MeasureWeightGPT OSS 20BERNIE 4.5 VL 424B A47B Qwen3 30B-A3B Instruct 2507
Price50%905785
Inputs & features30%353525
Context window20%252337
Overall100%61/10044/10057/100

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.

GPT OSS 20B vs ERNIE 4.5 VL 424B A47B vs Qwen3 30B-A3B Instruct 2507 specifications side by side
SpecificationGPT OSS 20BOpenAIERNIE 4.5 VL 424B A47B BaiduQwen3 30B-A3B Instruct 2507Alibaba (Qwen)
Capability
Capabilities Index (ECI)137.8 (best)—137.3
ECI rank#122 of 165 (best)—#124 of 165
GPQA DiamondGraduate-level science questions60.8% (best)—55.6%
OTIS Mock AIME 2024–2025Competition mathematics65.3% (best)—62.2%
Price per million tokens
Input$0.07 (best)$0.42$0.10
Output$0.25 (best)$1.25$0.30
Cached input———
Blended (3:1)$0.115 (best)$0.627$0.15
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 37 providersMedian of 1 providersMedian of 12 providers
Limits
Context window131,072 tokens123,000 tokens262,144 tokens (best)
Max output32,768 tokens (best)16,000 tokens16,384 tokens
Inputs and features
TextYesYesYes
ImagesNoYesNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesYesNo
Tool callingYesNoYes
Structured outputNoNoNo
Availability
WeightsOpenOpenOpenApache 2.0
API model ID———
API providers41 (best)114
ReleasedAug 5, 2025Jun 30, 2025Jul 28, 2025
Knowledge cutoffJun 2024Mar 31, 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.

  • GPT OSS 20B$1.20
  • ERNIE 4.5 VL 424B A47B $6.70
  • Qwen3 30B-A3B Instruct 2507$1.60
04 — Questions

Which should you choose?

Which is better: GPT OSS 20B, ERNIE 4.5 VL 424B A47B or Qwen3 30B-A3B Instruct 2507?

GPT OSS 20B is the better all-round choice, scoring 61/100 against Qwen3 30B-A3B Instruct 2507 (57) and ERNIE 4.5 VL 424B A47B (44). It leads on price. Qwen3 30B-A3B Instruct 2507 wins on context window. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, GPT OSS 20B, ERNIE 4.5 VL 424B A47B or Qwen3 30B-A3B Instruct 2507?

GPT OSS 20B is cheaper at $0.07 input / $0.25 output per million tokens (median across 37 API providers). Qwen3 30B-A3B Instruct 2507 costs $0.10 input / $0.30 output per million tokens (median across 12 API providers); ERNIE 4.5 VL 424B A47B costs $0.42 input / $1.25 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.115 per million tokens for GPT OSS 20B versus $0.15 for Qwen3 30B-A3B Instruct 2507 (1.3× as much) and $0.627 for ERNIE 4.5 VL 424B A47B (5.5× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. GPT OSS 20B has an ECI of 137.8, ERNIE 4.5 VL 424B A47B has not been scored yet and Qwen3 30B-A3B Instruct 2507 has an ECI of 137.3.

Which is better for coding?

There are no published SWE-bench Verified results for GPT OSS 20B, ERNIE 4.5 VL 424B A47B and Qwen3 30B-A3B Instruct 2507 yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that ERNIE 4.5 VL 424B A47B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Qwen3 30B-A3B Instruct 2507 has the largest context window at 262,144 tokens, against 131,072 for GPT OSS 20B and 123,000 for ERNIE 4.5 VL 424B A47B . Maximum output per response: GPT OSS 20B up to 32,768, ERNIE 4.5 VL 424B A47B up to 16,000, Qwen3 30B-A3B Instruct 2507 up to 16,384 tokens.

Which can read images, PDFs, audio or video?

GPT OSS 20B accepts text; ERNIE 4.5 VL 424B A47B accepts text and images; Qwen3 30B-A3B Instruct 2507 accepts text. ERNIE 4.5 VL 424B A47B handles the widest range of inputs.

Are any of these open source?

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

Which is newer?

GPT OSS 20B is the newest, released Aug 5, 2025. Qwen3 30B-A3B Instruct 2507 came out Jul 28, 2025; ERNIE 4.5 VL 424B A47B came out Jun 30, 2025. Knowledge cutoff: GPT OSS 20B Jun 2024, ERNIE 4.5 VL 424B A47B Mar 31, 2025.

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 Nov 2, 2026.

05 — Keep comparing

Related comparisons