Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 VL 235B A22B Instruct
Alibaba
- K2-V2 (High)
Institute of Foundation Models
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 VL 235B A22B Instruct Alibaba | K2-V2 (High) Institute of Foundation Models | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 9.9 | 9.9 | |
| Math | 70.7 | Best: 78.3 | |
| Speed | 28.5 t/s | — | |
| TTFT | 1.43 s | — | |
| Input · $ / 1M tokens | $0.215 | — | |
| Output · $ / 1M tokens | $1.39 | — | |
| Context window | 262K | Best: 512K | |
| Reasoning | No | Yes | |
| Open weights | Yes | Yes |
Intelligence
- Qwen3 VL 235B A22B Instruct
- 9.9
- K2-V2 (High)
- 9.9
Math
- Qwen3 VL 235B A22B Instruct
- 70.7
- K2-V2 (High)
- Best: 78.3
Speed
- Qwen3 VL 235B A22B Instruct
- 28.5 t/s
- K2-V2 (High)
- —
TTFT
- Qwen3 VL 235B A22B Instruct
- 1.43 s
- K2-V2 (High)
- —
Input · $ / 1M tokens
- Qwen3 VL 235B A22B Instruct
- $0.215
- K2-V2 (High)
- —
Output · $ / 1M tokens
- Qwen3 VL 235B A22B Instruct
- $1.39
- K2-V2 (High)
- —
Context window
- Qwen3 VL 235B A22B Instruct
- 262K
- K2-V2 (High)
- Best: 512K
Reasoning
- Qwen3 VL 235B A22B Instruct
- No
- K2-V2 (High)
- Yes
Open weights
- Qwen3 VL 235B A22B Instruct
- Yes
- K2-V2 (High)
- 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 VL 235B A22B Instruct9.9 · $0.509
Not plotted for lack of data on these axes: K2-V2 (High).