Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Seed-OSS-36B-Instruct
ByteDance
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Seed-OSS-36B-Instruct ByteDance | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | Best: 12.1 | 12 | |
| Math | 84.7 | — | |
| Speed | 40.9 t/s | — | |
| TTFT | 2.84 s | — | |
| Input · $ / 1M tokens | $0.21×2.3 relative to the lowest price among the compared models | Best: $0.090 | |
| Output · $ / 1M tokens | $0.57 | Best: $0.55 | |
| Context window | Best: 512K | 262K | |
| Reasoning | Yes | — | |
| Open weights | Yes | Yes |
Intelligence
- Seed-OSS-36B-Instruct
- Best: 12.1
- Qwen3 235B A22B Instruct 2507
- 12
Math
- Seed-OSS-36B-Instruct
- 84.7
- Qwen3 235B A22B Instruct 2507
- —
Speed
- Seed-OSS-36B-Instruct
- 40.9 t/s
- Qwen3 235B A22B Instruct 2507
- —
TTFT
- Seed-OSS-36B-Instruct
- 2.84 s
- Qwen3 235B A22B Instruct 2507
- —
Input · $ / 1M tokens
- Seed-OSS-36B-Instruct
- $0.21×2.3 relative to the lowest price among the compared models
- Qwen3 235B A22B Instruct 2507
- Best: $0.090
Output · $ / 1M tokens
- Seed-OSS-36B-Instruct
- $0.57
- Qwen3 235B A22B Instruct 2507
- Best: $0.55
Context window
- Seed-OSS-36B-Instruct
- Best: 512K
- Qwen3 235B A22B Instruct 2507
- 262K
Reasoning
- Seed-OSS-36B-Instruct
- Yes
- Qwen3 235B A22B Instruct 2507
- —
Open weights
- Seed-OSS-36B-Instruct
- Yes
- Qwen3 235B A22B Instruct 2507
- Yes
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.
- Seed-OSS-36B-Instruct12.1 · $0.30
- Qwen3 235B A22B Instruct 250712 · $0.205