Model Comparator
Compare up to four models using the same criteria.
2 models compared
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Add a model · 2/4 | ||
|---|---|---|---|
| Intelligence | Best: 11.2 | 11.1 | |
| Coding | 17.4 | Best: 22.4 | |
| Math | 84.3 | — | |
| Agentic | — | 1.3 | |
| Speed | Best: 163 t/s | 114 t/s | |
| TTFT | Best: 0.73 s | 0.85 s | |
| Input · $ / 1M tokens | $0.15×2.5 relative to the lowest price among the compared models | Best: $0.060 | |
| Output · $ / 1M tokens | $1.20×4.8 relative to the lowest price among the compared models | Best: $0.25 | |
| Context window | Best: 262K | 131K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | — | $0.0236 |
Intelligence
- Qwen3 Next 80B A3B (Reasoning)
- Best: 11.2
- Granite 4.2 8B
- 11.1
Coding
- Qwen3 Next 80B A3B (Reasoning)
- 17.4
- Granite 4.2 8B
- Best: 22.4
Math
- Qwen3 Next 80B A3B (Reasoning)
- 84.3
- Granite 4.2 8B
- —
Agentic
- Qwen3 Next 80B A3B (Reasoning)
- —
- Granite 4.2 8B
- 1.3
Speed
- Qwen3 Next 80B A3B (Reasoning)
- Best: 163 t/s
- Granite 4.2 8B
- 114 t/s
TTFT
- Qwen3 Next 80B A3B (Reasoning)
- Best: 0.73 s
- Granite 4.2 8B
- 0.85 s
Input · $ / 1M tokens
- Qwen3 Next 80B A3B (Reasoning)
- $0.15×2.5 relative to the lowest price among the compared models
- Granite 4.2 8B
- Best: $0.060
Output · $ / 1M tokens
- Qwen3 Next 80B A3B (Reasoning)
- $1.20×4.8 relative to the lowest price among the compared models
- Granite 4.2 8B
- Best: $0.25
Context window
- Qwen3 Next 80B A3B (Reasoning)
- Best: 262K
- Granite 4.2 8B
- 131K
Reasoning
- Qwen3 Next 80B A3B (Reasoning)
- Yes
- Granite 4.2 8B
- Yes
Open weights
- Qwen3 Next 80B A3B (Reasoning)
- Yes
- Granite 4.2 8B
- Yes
Cost / task
- Qwen3 Next 80B A3B (Reasoning)
- —
- Granite 4.2 8B
- $0.0236
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.
- Qwen3 Next 80B A3B (Reasoning)11.2 · $0.412
- Granite 4.2 8B11.1 · $0.107