Skip to content
ModelCap

Head-to-head comparison

gpt-oss-120b vs Qwen3 32B

gpt-oss-120b (OpenAI) and Qwen3 32B (Qwen) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 15 September 2026

As of 15 September 2026, gpt-oss-120b holds the stronger ModelCap Index position (#125 vs #127); and gpt-oss-120b is 1.6× cheaper per output token ($0.17/1M vs $0.28/1M).

Which should you choose?

Choose gpt-oss-120b if…

  • you want the stronger overall ModelCap Index position — #125 against #127 (34.8 vs 34.3 points).
  • API cost matters — $0.17/1M output tokens against $0.28/1M, about 1.6× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.037/1M against $0.08/1M.
  • you want provider choice — 20 listed API providers against 2.
  • you want the more recently listed model — gpt-oss-120b was listed 5 August 2025, Qwen3 32B 28 April 2025.

Choose Qwen3 32B if…

  • Arena coding is your yardstick — 1407 against 1391.

gpt-oss-120b vs Qwen3 32B: specs, pricing and context

Specification comparison of gpt-oss-120b and Qwen3 32B
Fieldgpt-oss-120bOpenAIQwen3 32BQwen
ModelCap Index position#125#127
Index score34.834.3
EvidenceMeasuredMeasured
Input price / 1M tokens$0.037$0.08
Output price / 1M tokens$0.17$0.28
Context window131K tokens131K tokens
Max output tokens118K16K
API providers listed202
Weight accessOpen weightsOpen weights
Input modalitiesTextText
First listed5 August 202528 April 2025
PublisherOpenAIQwen

Evidence: 2 public benchmark observations across 2 boards · 2 public benchmark observations across 2 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: gpt-oss-120b vs Qwen3 32B

Public benchmark boards where gpt-oss-120b or Qwen3 32B has a published result
Boardgpt-oss-120bQwen3 32BLeads
Arena codingArena (LMArena)13911383–139814071383–1431Qwen3 32B
SWE-benchSWE-bench (Princeton / SWE-agent team)26.0%—Only one result
BFCL V4UC Berkeley (Gorilla)—48.7Function callingOnly one result
AA Intelligence IndexArtificial Analysis12.3intelligence-index:v4.3:high—Only one result
AA Terminal-Bench 2.1Artificial Analysis26.2%terminal-bench:2.1:terminus-2:e2b:pass-at-1:3-repeats:source-model="gpt-oss-120b (high)":reasoning=true—Only one result
AA τ²-Bench TelecomArtificial Analysis65.8%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="gpt-oss-120b (high)":reasoning=true—Only one result
AA Humanity's Last ExamArtificial Analysis19.6%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="gpt-oss-120b (high)":reasoning=true—Only one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

gpt-oss-120b vs Qwen3 32B: common questions

Is gpt-oss-120b better than Qwen3 32B?

gpt-oss-120b ranks higher on the ModelCap Index as of 15 September 2026: #125 against #127. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it. Their published uncertainty intervals overlap, so the rank difference alone does not establish a reliable capability advantage for your workload.

Is gpt-oss-120b cheaper than Qwen3 32B?

gpt-oss-120b is cheaper on output tokens: $0.17/1M against $0.28/1M. Input tokens are $0.037/1M for gpt-oss-120b and $0.08/1M for Qwen3 32B. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens. For 1,000 requests with 2,000 input and 500 output tokens each (2M input + 0.5M output), the listed-rate estimate is $0.16 for gpt-oss-120b versus $0.30 for Qwen3 32B. gpt-oss-120b costs 47.0% less in this scenario. This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the selected endpoint before budgeting.

Which has the bigger context window, gpt-oss-120b or Qwen3 32B?

Both publish a 131K-token context window.

Which is better for coding, gpt-oss-120b or Qwen3 32B?

Arena coding: gpt-oss-120b 1391, Qwen3 32B 1407 — Qwen3 32B leads.

Are gpt-oss-120b and Qwen3 32B open-weight models?

gpt-oss-120b: Open weights. Qwen3 32B: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run gpt-oss-120b and Qwen3 32B?

ModelCap currently lists 20 API providers for gpt-oss-120b and 2 for Qwen3 32B, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this gpt-oss-120b vs Qwen3 32B comparison?

Every figure comes from the sealed ModelCap dataset published 15 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further