Skip to content
ModelCap

Head-to-head comparison

Gemma 3 27B vs gpt-oss-120b

Gemma 3 27B (Google) and gpt-oss-120b (OpenAI) 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 9 September 2026

As of 9 September 2026, gpt-oss-120b holds the stronger ModelCap Index position (#114 vs #115); gpt-oss-120b is 2.6× cheaper per output token ($0.17/1M vs $0.45/1M); and gpt-oss-120b ships open weights.

Which should you choose?

Choose Gemma 3 27B if…

  • ModelCap publishes no field on which Gemma 3 27B leads gpt-oss-120b for this pair.

Choose gpt-oss-120b if…

  • you want the stronger overall ModelCap Index position — #114 against #115 (35.9 vs 35.9 points).
  • API cost matters — $0.17/1M output tokens against $0.45/1M, about 2.6× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.037/1M against $0.08/1M.
  • you want to self-host: gpt-oss-120b ships open weights while Gemma 3 27B is gated access.
  • you want provider choice — 18 listed API providers against 4.
  • Arena coding is your yardstick — 1391 against 1358.
  • AA Intelligence Index is your yardstick — 12.3 against 4.9.
  • AA Terminal-Bench 2.1 is your yardstick — 26.2% against 4.5%.
  • AA τ²-Bench Telecom is your yardstick — 65.8% against 10.5%.
  • AA Humanity's Last Exam is your yardstick — 19.6% against 4.4%.
  • you want the more recently listed model — gpt-oss-120b was listed 5 August 2025, Gemma 3 27B 12 March 2025.

Gemma 3 27B vs gpt-oss-120b: specs, pricing and context

Specification comparison of Gemma 3 27B and gpt-oss-120b
FieldGemma 3 27BGooglegpt-oss-120bOpenAI
ModelCap Index position#115#114
Index score35.935.9
EvidenceMeasuredMeasured
Input price / 1M tokens$0.08$0.037
Output price / 1M tokens$0.45$0.17
Context window131K tokens131K tokens
Max output tokens118K118K
API providers listed418
Weight accessGated accessOpen weights
Input modalitiesText, ImageText
First listed12 March 20255 August 2025
PublisherGoogleOpenAI

Evidence: 3 public benchmark observations across 3 boards · 3 public benchmark observations across 3 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Gemma 3 27B vs gpt-oss-120b

Public benchmark boards where Gemma 3 27B or gpt-oss-120b has a published result
BoardGemma 3 27Bgpt-oss-120bLeads
Arena codingArena (LMArena)13581351–136513911383–1399gpt-oss-120b
SWE-benchSWE-bench (Princeton / SWE-agent team)—26.0%Only one result
BFCL V4UC Berkeley (Gorilla)29.5Prompt—Only one result
AA Intelligence IndexArtificial Analysis4.9intelligence-index:v4.3:non-reasoning12.3intelligence-index:v4.3:highgpt-oss-120b
AA Terminal-Bench 2.1Artificial Analysis4.5%terminal-bench:2.1:terminus-2:e2b:pass-at-1:3-repeats:source-model="Gemma 3 27B":reasoning=false26.2%terminal-bench:2.1:terminus-2:e2b:pass-at-1:3-repeats:source-model="gpt-oss-120b (high)":reasoning=truegpt-oss-120b
AA τ²-Bench TelecomArtificial Analysis10.5%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="Gemma 3 27B":reasoning=false65.8%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="gpt-oss-120b (high)":reasoning=truegpt-oss-120b
AA Humanity's Last ExamArtificial Analysis4.4%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="Gemma 3 27B":reasoning=false19.6%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="gpt-oss-120b (high)":reasoning=truegpt-oss-120b

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.

Gemma 3 27B vs gpt-oss-120b: common questions

Is Gemma 3 27B better than gpt-oss-120b?

gpt-oss-120b ranks higher on the ModelCap Index as of 9 September 2026: #114 against #115. 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 Gemma 3 27B cheaper than gpt-oss-120b?

gpt-oss-120b is cheaper on output tokens: $0.17/1M against $0.45/1M. Input tokens are $0.08/1M for Gemma 3 27B and $0.037/1M for gpt-oss-120b. 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 $0.39 for Gemma 3 27B versus $0.16 for gpt-oss-120b. gpt-oss-120b costs 58.7% 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, Gemma 3 27B or gpt-oss-120b?

Both publish a 131K-token context window.

Which is better for coding, Gemma 3 27B or gpt-oss-120b?

Arena coding: Gemma 3 27B 1358, gpt-oss-120b 1391 — gpt-oss-120b leads. AA Terminal-Bench 2.1: Gemma 3 27B 4.5%, gpt-oss-120b 26.2% — gpt-oss-120b leads.

Are Gemma 3 27B and gpt-oss-120b open-weight models?

Gemma 3 27B: Gated access. gpt-oss-120b: 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 Gemma 3 27B and gpt-oss-120b?

ModelCap currently lists 4 API providers for Gemma 3 27B and 18 for gpt-oss-120b, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Gemma 3 27B vs gpt-oss-120b comparison?

Every figure comes from the sealed ModelCap dataset published 9 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