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 | 34.6 | Best: 35.2 | |
| Coding | — | 62.3 | |
| Cyber Index | 58.0% | — | |
| Speed | 94.6 t/s | Best: 121 t/s | |
| TTFT | 2.05 s | Best: 1.36 s | |
| Input · $ / 1M tokens | $0.834×8.3 relative to the lowest price among the compared models | Best: $0.10 | |
| Output · $ / 1M tokens | $2.50×8.3 relative to the lowest price among the compared models | Best: $0.30 | |
| Context window | Best: 1.05M | 1M | |
| Reasoning | Yes | Yes | |
| Open weights | No | No | |
| Cost / task | $1.03 | — |
Intelligence
- Tencent Hy4
- 34.6
- Agnes 2.5 Pro Beta
- Best: 35.2
Coding
- Tencent Hy4
- —
- Agnes 2.5 Pro Beta
- 62.3
Cyber Index
- Tencent Hy4
- 58.0%
- Agnes 2.5 Pro Beta
- —
Speed
- Tencent Hy4
- 94.6 t/s
- Agnes 2.5 Pro Beta
- Best: 121 t/s
TTFT
- Tencent Hy4
- 2.05 s
- Agnes 2.5 Pro Beta
- Best: 1.36 s
Input · $ / 1M tokens
- Tencent Hy4
- $0.834×8.3 relative to the lowest price among the compared models
- Agnes 2.5 Pro Beta
- Best: $0.10
Output · $ / 1M tokens
- Tencent Hy4
- $2.50×8.3 relative to the lowest price among the compared models
- Agnes 2.5 Pro Beta
- Best: $0.30
Context window
- Tencent Hy4
- Best: 1.05M
- Agnes 2.5 Pro Beta
- 1M
Reasoning
- Tencent Hy4
- Yes
- Agnes 2.5 Pro Beta
- Yes
Open weights
- Tencent Hy4
- No
- Agnes 2.5 Pro Beta
- No
Cost / task
- Tencent Hy4
- $1.03
- Agnes 2.5 Pro Beta
- —
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.
- Tencent Hy434.6 · $0.625
- Agnes 2.5 Pro Beta35.2 · $0.15