ZMIME
Comparison · 3 models · Updated Oct 4, 2026

GPT-5 Nano vs GPT OSS 120B vs Qwen3 235B-A22B Instruct 2507

GPT-5 Nano comes out ahead, 70 to 61 and 58 on our weighted score, and it is the cheaper option too.

  1. Our pick

    OpenAI

    GPT-5 Nano

    Released Aug 7, 2025

    70/100
    • ECI139.4
    • Price$0.05 / $0.40
    • Context400K
    Full specs Remove GPT-5 Nano

  2. 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. Alibaba (Qwen)

    Qwen3 235B-A22B Instruct 2507

    Released Jul 21, 2025

    58/100
    • ECI138.9
    • Price$0.15 / $0.75
    • Context262K
    Full specs Remove Qwen3 235B-A22B Instruct 2507
01 — Verdict

GPT-5 Nano is our pick

GPT-5 Nano is the better all-round choice, scoring 70/100 against GPT OSS 120B (61) and Qwen3 235B-A22B Instruct 2507 (58). It leads on price, 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 · GPT-5 Nano 139.4 · Qwen3 235B-A22B Instruct 2507 138.9
  • Lowest priceGPT-5 NanoGPT-5 Nano $0.138 · GPT OSS 120B $0.263 · Qwen3 235B-A22B Instruct 2507 $0.30 per 1M tokens (3:1 blend)
  • Longest contextGPT-5 NanoGPT-5 Nano 400,000 · Qwen3 235B-A22B Instruct 2507 262,144 · GPT OSS 120B 131,072 tokens
  • Widest inputsGPT-5 NanoGPT-5 Nano: Text, Images · GPT OSS 120B: Text · Qwen3 235B-A22B Instruct 2507: Text
  • Self-hostingGPT OSS 120B and Qwen3 235B-A22B Instruct 2507Publishes downloadable weights (Apache 2.0)
How the score is built
MeasureWeightGPT-5 NanoGPT OSS 120BQwen3 235B-A22B Instruct 2507
CapabilityCapabilities Index (ECI)50%656564
Price25%917775
Inputs & features15%704525
Context window10%442437
Overall100%70/10061/10058/100
02 — Side by side

Every spec in one table

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

GPT-5 Nano vs GPT OSS 120B vs Qwen3 235B-A22B Instruct 2507 specifications side by side
SpecificationGPT-5 NanoOpenAIGPT OSS 120BOpenAIQwen3 235B-A22B Instruct 2507Alibaba (Qwen)
Capability
Capabilities Index (ECI)139.4140.0 (best)138.9
ECI rank#102 of 148#99 of 148 (best)#105 of 148
GPQA DiamondGraduate-level science questions69.4%75.8% (best)—
FrontierMath Tiers 1–3Research-level mathematics20.0%——
OTIS Mock AIME 2024–2025Competition mathematics81.1%88.9% (best)—
SimpleQA VerifiedShort factual questions11.7%——
Price per million tokens
Input$0.05 (best)$0.15$0.15
Output$0.40 (best)$0.60$0.75
Cached input$0.005——
Blended (3:1)$0.138 (best)$0.263$0.30
Long-context rateSame rateSame rateSame rate
Price sourceOfficial OpenAI APIMedian of 36 providersMedian of 11 providers
Limits
Context window400,000 tokens (best)131,072 tokens262,144 tokens
Max output128,000 tokens (best)32,768 tokens16,384 tokens
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsNoNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningYesminimal · low · medium · highYesNo
Tool callingYesYesYes
Structured outputYesYesNo
Availability
WeightsProprietaryOpenOpenApache 2.0
API model IDgpt-5-nano——
API providers2139 (best)11
ReleasedAug 7, 2025Aug 5, 2025Jul 21, 2025
Knowledge cutoffMay 30, 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.

  • GPT-5 Nano$1.30
  • GPT OSS 120B$2.70
  • Qwen3 235B-A22B Instruct 2507$3.00
04 — Questions

Which should you choose?

Which is better: GPT-5 Nano, GPT OSS 120B or Qwen3 235B-A22B Instruct 2507?

GPT-5 Nano is the better all-round choice, scoring 70/100 against GPT OSS 120B (61) and Qwen3 235B-A22B Instruct 2507 (58). It leads on price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, GPT-5 Nano, GPT OSS 120B or Qwen3 235B-A22B Instruct 2507?

GPT-5 Nano is cheaper at $0.05 input / $0.40 output per million tokens (official OpenAI API price). GPT OSS 120B costs $0.15 input / $0.60 output per million tokens (median across 36 API providers); Qwen3 235B-A22B Instruct 2507 costs $0.15 input / $0.75 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $0.138 per million tokens for GPT-5 Nano versus $0.263 for GPT OSS 120B (1.9× as much) and $0.30 for Qwen3 235B-A22B Instruct 2507 (2.2× 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), GPT-5 Nano 139.4 (#102 of 148) and Qwen3 235B-A22B Instruct 2507 138.9 (#105 of 148). The confidence ranges of the top two overlap (135.3–142.3 vs 134.9–141.7), so treat the gap as small.

Which is better for coding?

There are no published SWE-bench Verified results for GPT-5 Nano, GPT OSS 120B and Qwen3 235B-A22B Instruct 2507 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?

GPT-5 Nano has the largest context window at 400,000 tokens, against 262,144 for Qwen3 235B-A22B Instruct 2507 and 131,072 for GPT OSS 120B. Maximum output per response: GPT-5 Nano up to 128,000, GPT OSS 120B up to 32,768, Qwen3 235B-A22B Instruct 2507 up to 16,384 tokens.

Which can read images, PDFs, audio or video?

GPT-5 Nano accepts text and images; GPT OSS 120B accepts text; Qwen3 235B-A22B Instruct 2507 accepts text. GPT-5 Nano handles the widest range of inputs.

Are any of these open source?

GPT OSS 120B and Qwen3 235B-A22B Instruct 2507 publishes its weights (Apache 2.0) and can be self-hosted; GPT-5 Nano is proprietary.

Which is newer?

GPT-5 Nano is the newest, released Aug 7, 2025. GPT OSS 120B came out Aug 5, 2025; Qwen3 235B-A22B Instruct 2507 came out Jul 21, 2025. Knowledge cutoff: GPT-5 Nano May 30, 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