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 | 9.8 | 9.8 | |
| Coding | 12.1 | 12.1 | |
| Math | — | 56.3 | |
| Agentic | 0.9 | 0.9 | |
| Speed | — | 135 t/s | |
| TTFT | — | 2.46 s | |
| Input · $ / 1M tokens | Best: $0.20 | $0.36×1.8 relative to the lowest price among the compared models | |
| Output · $ / 1M tokens | $2.40×1.8 relative to the lowest price among the compared models | Best: $1.30 | |
| Context window | 81.9K | Best: 262K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes | |
| Cost / task | — | $0.0659 |
Intelligence
- Qwen3 30B A3B Thinking 2507
- 9.8
- Qwen3 30B A3B 2507 (Reasoning)
- 9.8
Coding
- Qwen3 30B A3B Thinking 2507
- 12.1
- Qwen3 30B A3B 2507 (Reasoning)
- 12.1
Math
- Qwen3 30B A3B Thinking 2507
- —
- Qwen3 30B A3B 2507 (Reasoning)
- 56.3
Agentic
- Qwen3 30B A3B Thinking 2507
- 0.9
- Qwen3 30B A3B 2507 (Reasoning)
- 0.9
Speed
- Qwen3 30B A3B Thinking 2507
- —
- Qwen3 30B A3B 2507 (Reasoning)
- 135 t/s
TTFT
- Qwen3 30B A3B Thinking 2507
- —
- Qwen3 30B A3B 2507 (Reasoning)
- 2.46 s
Input · $ / 1M tokens
- Qwen3 30B A3B Thinking 2507
- Best: $0.20
- Qwen3 30B A3B 2507 (Reasoning)
- $0.36×1.8 relative to the lowest price among the compared models
Output · $ / 1M tokens
- Qwen3 30B A3B Thinking 2507
- $2.40×1.8 relative to the lowest price among the compared models
- Qwen3 30B A3B 2507 (Reasoning)
- Best: $1.30
Context window
- Qwen3 30B A3B Thinking 2507
- 81.9K
- Qwen3 30B A3B 2507 (Reasoning)
- Best: 262K
Reasoning
- Qwen3 30B A3B Thinking 2507
- Yes
- Qwen3 30B A3B 2507 (Reasoning)
- Yes
Open weights
- Qwen3 30B A3B Thinking 2507
- Yes
- Qwen3 30B A3B 2507 (Reasoning)
- Yes
Cost / task
- Qwen3 30B A3B Thinking 2507
- —
- Qwen3 30B A3B 2507 (Reasoning)
- $0.0659
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 30B A3B Thinking 25079.8 · $0.75
- Qwen3 30B A3B 2507 (Reasoning)9.8 · $0.595