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 | 12.7 | 12.7 | |
| Coding | 22.1 | Best: 29.9 | |
| Math | 91 | — | |
| Agentic | 1.3 | Best: 3.5 | |
| Speed | Best: 85.4 t/s | 75.5 t/s | |
| TTFT | Best: 0.8 s | 0.87 s | |
| Input · $ / 1M tokens | $0.23×1.4 relative to the lowest price among the compared models | Best: $0.16 | |
| Output · $ / 1M tokens | $2.30×3.5 relative to the lowest price among the compared models | Best: $0.65 | |
| Context window | Best: 256K | 131K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | $0.0806×1.1 relative to the lowest price among the compared models | Best: $0.0717 |
Intelligence
- Qwen3 235B A22B 2507 (Reasoning)
- 12.7
- Granite 4.2 30B
- 12.7
Coding
- Qwen3 235B A22B 2507 (Reasoning)
- 22.1
- Granite 4.2 30B
- Best: 29.9
Math
- Qwen3 235B A22B 2507 (Reasoning)
- 91
- Granite 4.2 30B
- —
Agentic
- Qwen3 235B A22B 2507 (Reasoning)
- 1.3
- Granite 4.2 30B
- Best: 3.5
Speed
- Qwen3 235B A22B 2507 (Reasoning)
- Best: 85.4 t/s
- Granite 4.2 30B
- 75.5 t/s
TTFT
- Qwen3 235B A22B 2507 (Reasoning)
- Best: 0.8 s
- Granite 4.2 30B
- 0.87 s
Input · $ / 1M tokens
- Qwen3 235B A22B 2507 (Reasoning)
- $0.23×1.4 relative to the lowest price among the compared models
- Granite 4.2 30B
- Best: $0.16
Output · $ / 1M tokens
- Qwen3 235B A22B 2507 (Reasoning)
- $2.30×3.5 relative to the lowest price among the compared models
- Granite 4.2 30B
- Best: $0.65
Context window
- Qwen3 235B A22B 2507 (Reasoning)
- Best: 256K
- Granite 4.2 30B
- 131K
Reasoning
- Qwen3 235B A22B 2507 (Reasoning)
- Yes
- Granite 4.2 30B
- Yes
Open weights
- Qwen3 235B A22B 2507 (Reasoning)
- Yes
- Granite 4.2 30B
- Yes
Cost / task
- Qwen3 235B A22B 2507 (Reasoning)
- $0.0806×1.1 relative to the lowest price among the compared models
- Granite 4.2 30B
- Best: $0.0717
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 235B A22B 2507 (Reasoning)12.7 · $0.0806
- Granite 4.2 30B12.7 · $0.0717