// head_to_head
Ling 3.0 Tiny vs gpt-oss-120b
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Ling 3.0 Tiny is the cheaper of the two; neither can be ranked on quality here.
Neither model has a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
inclusionai
Ling 3.0 Tiny
- Blended / 1M
- $0.022
- Context
- 262K
- Released
- Aug 6, 2026
- Overall score
- Not evaluated
openai
gpt-oss-120b
- Blended / 1M
- $0.032
- Context
- 131K
- Released
- Aug 5, 2025
- Overall score
- Not evaluated
Specs and pricing
| Metric | Ling 3.0 Tiny | gpt-oss-120b |
|---|---|---|
| LiveBench overall Weighted mean of the seven LiveBench category scores, 0–100. Higher is better. | — | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | — | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $0.022win | $0.032 |
| Input price / 1M | $0.015win | $0.019 |
| Output price / 1M | $0.045win | $0.072 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.0030win | $0.017 |
| Context window | 262Kwin | 131K |
| Max output tokens | 250Kwin | 66K |
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | Ling 3.0 Tiny | gpt-oss-120b |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $6.34/mo | $10.18/mo |
| RAG assistant 8K in / 600 out × 100K requests | $9.90/mo | $18.72/mo |
| Coding agent 40K in / 4K out × 20K requests | $8.88/mo | $19.84/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $17.78/mo | $24.30/mo |
| Bulk classification 500 in / 20 out × 5M requests | $36.00/mo | $53.70/mo |
Which should you pick?
You need to fit large documents in one call
Ling 3.0 Tiny
Wider context window — 262K against 131K.
Ling 3.0 Tiny vs gpt-oss-120b FAQ
Which is better, Ling 3.0 Tiny or gpt-oss-120b?
Ling 3.0 Tiny is the cheaper of the two; neither can be ranked on quality here. Neither model has a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is Ling 3.0 Tiny cheaper than gpt-oss-120b?
Ling 3.0 Tiny is cheaper. On a 3:1 input:output blend, Ling 3.0 Tiny lists at $0.022 per million tokens and gpt-oss-120b at $0.032 — Ling 3.0 Tiny is 43% cheaper. Input and output are priced separately — Ling 3.0 Tiny charges $0.015 in and $0.045 out, gpt-oss-120b charges $0.019 and $0.072 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does Ling 3.0 Tiny or gpt-oss-120b have a bigger context window?
Ling 3.0 Tiny has the larger context window: 262K for Ling 3.0 Tiny against 131K for gpt-oss-120b. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do Ling 3.0 Tiny and gpt-oss-120b support prompt caching?
Both publish a cached-input rate: $0.0030 per million for Ling 3.0 Tiny and $0.017 for gpt-oss-120b, against full input rates of $0.015 and $0.019. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-10-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.