gpt-oss-20b vs Llama 4 Scout
| Spec | gpt-oss-20b | Llama 4 Scout |
|---|---|---|
| Respan Index | 13.6 (#165) | 11.2 (#167) |
| Blended price per 1M | $0.036 | $0.15 |
| Context window | 131K | 10M |
| Input / output per 1M | $0.018 / $0.09 | $0.1 / $0.3 |
| Max output | 131K | - |
| Input | text | text, vision |
| Released | 2025-08-05 | 2025-04-05 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | gpt-oss-20b | Llama 4 Scout |
|---|---|---|
| Coding | 4.7 gpt-oss-20b | 0.7* Llama 4 Scout |
| Agents | 7.8* gpt-oss-20b | 3.8* Llama 4 Scout |
| Reasoning | 18.5 gpt-oss-20b | 16.8 Llama 4 Scout |
| Knowledge & language | 7.0* gpt-oss-20b | 6.6 Llama 4 Scout |
| Human preference | 34.5 gpt-oss-20b | 34.7 Llama 4 Scout |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
gpt-oss-20b leads on 2 of the 3 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | gpt-oss-20b | Llama 4 Scout |
|---|---|---|
| LMArena Elo | 1318 | 1322 |
| GPQA Diamond | 71.5% | 57.2% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 65.3% | 7.8% |
FAQ
Is gpt-oss-20b better than Llama 4 Scout?
gpt-oss-20b scores 13.6 on the Respan Index (#165), ahead of Llama 4 Scout at 11.2 (#167). gpt-oss-20b leads on 2 of the 3 benchmarks both report.
Which is cheaper, gpt-oss-20b or Llama 4 Scout?
gpt-oss-20b lists at $0.018 input and $0.09 output per 1M tokens; Llama 4 Scout at $0.1 and $0.3. gpt-oss-20b is 4.2x cheaper per token at list price.
Which has the larger context window?
gpt-oss-20b accepts 131K tokens and Llama 4 Scout 10M tokens.