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 | 11.1 | Best: 11.2 | |
| Coding | Best: 22.4 | 17.4 | |
| Math | — | 84.3 | |
| Agentic | 1.3 | — | |
| Speed | 120 t/s | Best: 163 t/s | |
| TTFT | 0.77 s | Best: 0.69 s | |
| Input · $ / 1M tokens | Best: $0.060 | $0.15×2.5 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | Best: $0.25 | $1.20×4.8 relative to the lowest price among the compared models | |
| Context window | 131K | Best: 262K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.0236 | — |
Intelligence
- Granite 4.2 8B
- 11.1
- Qwen3 Next 80B A3B (Reasoning)
- Best: 11.2
Coding
- Granite 4.2 8B
- Best: 22.4
- Qwen3 Next 80B A3B (Reasoning)
- 17.4
Math
- Granite 4.2 8B
- —
- Qwen3 Next 80B A3B (Reasoning)
- 84.3
Agentic
- Granite 4.2 8B
- 1.3
- Qwen3 Next 80B A3B (Reasoning)
- —
Speed
- Granite 4.2 8B
- 120 t/s
- Qwen3 Next 80B A3B (Reasoning)
- Best: 163 t/s
TTFT
- Granite 4.2 8B
- 0.77 s
- Qwen3 Next 80B A3B (Reasoning)
- Best: 0.69 s
Input · $ / 1M tokens
- Granite 4.2 8B
- Best: $0.060
- Qwen3 Next 80B A3B (Reasoning)
- $0.15×2.5 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Granite 4.2 8B
- Best: $0.25
- Qwen3 Next 80B A3B (Reasoning)
- $1.20×4.8 relative to the lowest price among the compared models
Context window
- Granite 4.2 8B
- 131K
- Qwen3 Next 80B A3B (Reasoning)
- Best: 262K
Reasoning
- Granite 4.2 8B
- Yes
- Qwen3 Next 80B A3B (Reasoning)
- Yes
Open weights
- Granite 4.2 8B
- Yes
- Qwen3 Next 80B A3B (Reasoning)
- Yes
Cost / task
- Granite 4.2 8B
- $0.0236
- Qwen3 Next 80B A3B (Reasoning)
- —
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.
- Granite 4.2 8B11.1 · $0.107
- Qwen3 Next 80B A3B (Reasoning)11.2 · $0.412