Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 235B A22B (Reasoning)
Alibaba
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 235B A22B (Reasoning) Alibaba | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 9.5 | 9.5 | |
| Math | 82 | — | |
| Speed | 64 t/s | — | |
| TTFT | 2.88 s | — | |
| Input · $ / 1M tokens | $0.70×2.4 relative to the lowest price among the compared models | Best: $0.29 | |
| Output · $ / 1M tokens | $8.40×8.4 relative to the lowest price among the compared models | Best: $1 | |
| Context window | 33K | Best: 262K | |
| Reasoning | Yes | Yes | |
| Open weights | Yes | Yes |
Intelligence
- Qwen3 235B A22B (Reasoning)
- 9.5
- Qwen3 VL 30B A3B Thinking
- 9.5
Math
- Qwen3 235B A22B (Reasoning)
- 82
- Qwen3 VL 30B A3B Thinking
- —
Speed
- Qwen3 235B A22B (Reasoning)
- 64 t/s
- Qwen3 VL 30B A3B Thinking
- —
TTFT
- Qwen3 235B A22B (Reasoning)
- 2.88 s
- Qwen3 VL 30B A3B Thinking
- —
Input · $ / 1M tokens
- Qwen3 235B A22B (Reasoning)
- $0.70×2.4 relative to the lowest price among the compared models
- Qwen3 VL 30B A3B Thinking
- Best: $0.29
Output · $ / 1M tokens
- Qwen3 235B A22B (Reasoning)
- $8.40×8.4 relative to the lowest price among the compared models
- Qwen3 VL 30B A3B Thinking
- Best: $1
Context window
- Qwen3 235B A22B (Reasoning)
- 33K
- Qwen3 VL 30B A3B Thinking
- Best: 262K
Reasoning
- Qwen3 235B A22B (Reasoning)
- Yes
- Qwen3 VL 30B A3B Thinking
- Yes
Open weights
- Qwen3 235B A22B (Reasoning)
- Yes
- Qwen3 VL 30B A3B Thinking
- 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.
- Qwen3 235B A22B (Reasoning)9.5 · $2.63
- Qwen3 VL 30B A3B Thinking9.5 · $0.467