Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Reka Flash 3
Reka AI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Reka Flash 3 Reka AI | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 6.4 | 6.4 | |
| Math | 33.7 | — | |
| Speed | 93.6 t/s | — | |
| TTFT | 1.35 s | — | |
| Input · $ / 1M tokens | $0.10 | — | |
| Output · $ / 1M tokens | $0.20 | — | |
| Context window | Best: 1M | 128K | |
| Reasoning | Yes | No | |
| Open weights | Yes | Yes |
Intelligence
- Reka Flash 3
- 6.4
- Llama 3.2 Instruct 90B (Vision)
- 6.4
Math
- Reka Flash 3
- 33.7
- Llama 3.2 Instruct 90B (Vision)
- —
Speed
- Reka Flash 3
- 93.6 t/s
- Llama 3.2 Instruct 90B (Vision)
- —
TTFT
- Reka Flash 3
- 1.35 s
- Llama 3.2 Instruct 90B (Vision)
- —
Input · $ / 1M tokens
- Reka Flash 3
- $0.10
- Llama 3.2 Instruct 90B (Vision)
- —
Output · $ / 1M tokens
- Reka Flash 3
- $0.20
- Llama 3.2 Instruct 90B (Vision)
- —
Context window
- Reka Flash 3
- Best: 1M
- Llama 3.2 Instruct 90B (Vision)
- 128K
Reasoning
- Reka Flash 3
- Yes
- Llama 3.2 Instruct 90B (Vision)
- No
Open weights
- Reka Flash 3
- Yes
- Llama 3.2 Instruct 90B (Vision)
- 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.
- Reka Flash 36.4 · $0.125
Not plotted for lack of data on these axes: Llama 3.2 Instruct 90B (Vision).