Skip to content
ModelCap

Head-to-head comparison

GPT-5.6 Terra vs gpt-oss-120b

GPT-5.6 Terra (OpenAI) 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 22 September 2026

As of 22 September 2026, GPT-5.6 Terra holds the stronger ModelCap Index position (#21 vs #131); gpt-oss-120b is 20× cheaper per output token ($0.60/1M vs $12.00/1M); GPT-5.6 Terra offers the longer context window (1M vs 131K tokens); and gpt-oss-120b ships open weights.

Which should you choose?

Choose GPT-5.6 Terra if…

  • you want the stronger overall ModelCap Index position — #21 against #131 (79.7 vs 43.3 points).
  • you need the longer context window — 1M tokens against 131K.
  • Arena coding is your yardstick — 1518 against 1391.
  • AA Intelligence Index is your yardstick — 42.1 against 11.6.
  • AA τ²-Bench Telecom is your yardstick — 86.3% against 65.8%.
  • AA Humanity's Last Exam is your yardstick — 42.9% against 19.6%.
  • you want the more recently listed model — GPT-5.6 Terra was listed 9 July 2026, gpt-oss-120b 5 August 2025.

Choose gpt-oss-120b if…

  • API cost matters — $0.60/1M output tokens against $12.00/1M, about 20× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.15/1M against $2.00/1M.
  • you want to self-host: gpt-oss-120b ships open weights while GPT-5.6 Terra is api only.
  • you want provider choice — 20 listed API providers against 3.

GPT-5.6 Terra vs gpt-oss-120b: specs, pricing and context

Specification comparison of GPT-5.6 Terra and gpt-oss-120b
FieldGPT-5.6 TerraOpenAIgpt-oss-120bOpenAI
ModelCap Index position#21#131
Index score79.743.3
EvidenceMeasuredMeasured
Input price / 1M tokens$2.00$0.15
Output price / 1M tokens$12.00$0.60
Context window1M tokens131K tokens
Max output tokens128K66K
API providers listed320
Weight accessAPI onlyOpen weights
Input modalitiesFile, Image, TextText
First listed9 July 20265 August 2025
PublisherOpenAIOpenAI

Evidence: 6 public benchmark observations across 6 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: GPT-5.6 Terra vs gpt-oss-120b

Public benchmark boards where GPT-5.6 Terra or gpt-oss-120b has a published result
BoardGPT-5.6 Terragpt-oss-120bLeads
Arena codingArena (LMArena)15181510–1525X-High13911383–1398GPT-5.6 Terra
LMArena AgentLMArena1.4%0.3%–2.6%X-High—Only one result
ARC-AGI-2ARC Prize Foundation83.9%Max—Only one result
ARC-AGI-3ARC Prize Foundation0.8%Max—Only one result
SWE-benchSWE-bench (Princeton / SWE-agent team)—26.0%Only one result
AA Intelligence IndexArtificial Analysis42.1intelligence-index:v4.3:max11.6intelligence-index:v4.3:highGPT-5.6 Terra
AA τ²-Bench TelecomArtificial Analysis86.3%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="GPT-5.6 Terra (max)":reasoning=true65.8%tau2:telecom:dual-control:pass-at-1:3-repeats:source-model="gpt-oss-120b (high)":reasoning=trueGPT-5.6 Terra
AA Humanity's Last ExamArtificial Analysis42.9%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="GPT-5.6 Terra (max)":reasoning=true19.6%hle:may-2025:text-only-2158:no-tools:pass-at-1:source-model="gpt-oss-120b (high)":reasoning=trueGPT-5.6 Terra
Terminal-Bench 4.0Terminal-Bench (Laude Institute)21.5%18.3%–24.8%Codex · Max—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-5.6 Terra vs gpt-oss-120b: common questions

Is GPT-5.6 Terra better than gpt-oss-120b?

GPT-5.6 Terra ranks higher on the ModelCap Index as of 22 September 2026: #21 against #131. 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 do not overlap, but the aggregate Index does not predict performance on every task; compare the relevant benchmark configurations before choosing.

Is GPT-5.6 Terra cheaper than gpt-oss-120b?

gpt-oss-120b is cheaper on output tokens: $0.60/1M against $12.00/1M. Input tokens are $2.00/1M for GPT-5.6 Terra and $0.15/1M 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 $10.00 for GPT-5.6 Terra versus $0.60 for gpt-oss-120b. gpt-oss-120b costs 94.0% 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-5.6 Terra or gpt-oss-120b?

GPT-5.6 Terra has the larger context window: 1M tokens against 131K.

Which is better for coding, GPT-5.6 Terra or gpt-oss-120b?

Arena coding: GPT-5.6 Terra 1518, gpt-oss-120b 1391 — GPT-5.6 Terra leads.

Are GPT-5.6 Terra and gpt-oss-120b open-weight models?

GPT-5.6 Terra: API only. 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 GPT-5.6 Terra and gpt-oss-120b?

ModelCap currently lists 3 API providers for GPT-5.6 Terra and 20 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 GPT-5.6 Terra vs gpt-oss-120b comparison?

Every figure comes from the sealed ModelCap dataset published 22 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