Model Comparator
Compare up to four models using the same criteria.
2 models compared
- gpt-oss-20b (High)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | gpt-oss-20b (High) OpenAI | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 9 | Best: 9.1 | |
| Coding | Best: 20.7 | 17.5 | |
| Math | 89.3 | — | |
| Agentic | Best: 1.2 | 0.9 | |
| Speed | Best: 226 t/s | 219 t/s | |
| TTFT | 0.73 s | Best: 0.53 s | |
| Input · $ / 1M tokens | $0.070×2.3 relative to the lowest price among the compared models | Best: $0.030 | |
| Output · $ / 1M tokens | $0.18×1.5 relative to the lowest price among the compared models | Best: $0.12 | |
| Context window | 131K | 131K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.0125×2.1 relative to the lowest price among the compared models | Best: $0.0060 |
Intelligence
- gpt-oss-20b (High)
- 9
- Granite 4.2 3B
- Best: 9.1
Coding
- gpt-oss-20b (High)
- Best: 20.7
- Granite 4.2 3B
- 17.5
Math
- gpt-oss-20b (High)
- 89.3
- Granite 4.2 3B
- —
Agentic
- gpt-oss-20b (High)
- Best: 1.2
- Granite 4.2 3B
- 0.9
Speed
- gpt-oss-20b (High)
- Best: 226 t/s
- Granite 4.2 3B
- 219 t/s
TTFT
- gpt-oss-20b (High)
- 0.73 s
- Granite 4.2 3B
- Best: 0.53 s
Input · $ / 1M tokens
- gpt-oss-20b (High)
- $0.070×2.3 relative to the lowest price among the compared models
- Granite 4.2 3B
- Best: $0.030
Output · $ / 1M tokens
- gpt-oss-20b (High)
- $0.18×1.5 relative to the lowest price among the compared models
- Granite 4.2 3B
- Best: $0.12
Context window
- gpt-oss-20b (High)
- 131K
- Granite 4.2 3B
- 131K
Reasoning
- gpt-oss-20b (High)
- Yes
- Granite 4.2 3B
- Yes
Open weights
- gpt-oss-20b (High)
- Yes
- Granite 4.2 3B
- Yes
Cost / task
- gpt-oss-20b (High)
- $0.0125×2.1 relative to the lowest price among the compared models
- Granite 4.2 3B
- Best: $0.0060
Each reasoning level remains a separate configuration.
Score and cost
Each line joins the reasoning levels of a compared model; the large point marks the configuration in the table. The top-right corner holds the best score for the lowest cost. Select another point to compare that level.
- gpt-oss-20b (High)9 · $0.0125
- Granite 4.2 3B9.1 · $0.0060