Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Qwen3 14B (Non-reasoning)
Alibaba
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
Nous Research
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Qwen3 14B (Non-reasoning) Alibaba | Hermes 4 - Llama-3.1 70B (Non-reasoning) Nous Research | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 6.7 | 6.7 | |
| Math | Best: 58 | 11.3 | |
| Speed | 28.3 t/s | — | |
| TTFT | 1.23 s | — | |
| Input · $ / 1M tokens | $0.12 | — | |
| Output · $ / 1M tokens | $0.24 | — | |
| Context window | 33K | Best: 128K | |
| Reasoning | No | No | |
| Open weights | Yes | Yes |
Intelligence
- Qwen3 14B (Non-reasoning)
- 6.7
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- 6.7
Math
- Qwen3 14B (Non-reasoning)
- Best: 58
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- 11.3
Speed
- Qwen3 14B (Non-reasoning)
- 28.3 t/s
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- —
TTFT
- Qwen3 14B (Non-reasoning)
- 1.23 s
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- —
Input · $ / 1M tokens
- Qwen3 14B (Non-reasoning)
- $0.12
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- —
Output · $ / 1M tokens
- Qwen3 14B (Non-reasoning)
- $0.24
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- —
Context window
- Qwen3 14B (Non-reasoning)
- 33K
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- Best: 128K
Reasoning
- Qwen3 14B (Non-reasoning)
- No
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- No
Open weights
- Qwen3 14B (Non-reasoning)
- Yes
- Hermes 4 - Llama-3.1 70B (Non-reasoning)
- 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 14B (Non-reasoning)6.7 · $0.15
Not plotted for lack of data on these axes: Hermes 4 - Llama-3.1 70B (Non-reasoning).