Model Comparator
Compare up to four models using the same criteria.
2 models compared
- gpt-oss-20b (High)
OpenAI
- Tri-21B-Think
Trillion Labs
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | gpt-oss-20b (High) OpenAI | Tri-21B-Think Trillion Labs | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 9 | 9 | |
| Coding | 20.7 | — | |
| Math | 89.3 | — | |
| Agentic | 1.2 | — | |
| Speed | 226 t/s | — | |
| TTFT | 0.73 s | — | |
| Input · $ / 1M tokens | $0.070 | — | |
| Output · $ / 1M tokens | $0.18 | — | |
| Context window | Best: 131K | 32K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.0125 | — |
Intelligence
- gpt-oss-20b (High)
- 9
- Tri-21B-Think
- 9
Coding
- gpt-oss-20b (High)
- 20.7
- Tri-21B-Think
- —
Math
- gpt-oss-20b (High)
- 89.3
- Tri-21B-Think
- —
Agentic
- gpt-oss-20b (High)
- 1.2
- Tri-21B-Think
- —
Speed
- gpt-oss-20b (High)
- 226 t/s
- Tri-21B-Think
- —
TTFT
- gpt-oss-20b (High)
- 0.73 s
- Tri-21B-Think
- —
Input · $ / 1M tokens
- gpt-oss-20b (High)
- $0.070
- Tri-21B-Think
- —
Output · $ / 1M tokens
- gpt-oss-20b (High)
- $0.18
- Tri-21B-Think
- —
Context window
- gpt-oss-20b (High)
- Best: 131K
- Tri-21B-Think
- 32K
Reasoning
- gpt-oss-20b (High)
- Yes
- Tri-21B-Think
- Yes
Open weights
- gpt-oss-20b (High)
- Yes
- Tri-21B-Think
- Yes
Cost / task
- gpt-oss-20b (High)
- $0.0125
- Tri-21B-Think
- —
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
Not plotted for lack of data on these axes: Tri-21B-Think.