Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude 2.1
Anthropic
- Reka Flash 3
Reka AI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude 2.1 Anthropic | Reka Flash 3 Reka AI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 5.6 | 5.6 | |
| Coding | 14 | — | |
| Math | — | 33.7 | |
| Speed | — | 87.6 t/s | |
| TTFT | — | 1.44 s | |
| Input · $ / 1M tokens | — | $0.20 | |
| Output · $ / 1M tokens | — | $0.80 | |
| Context window | Best: 200K | 128K | |
| Reasoning | No | Yes | |
| Open weights | No | Yes |
Intelligence
- Claude 2.1
- 5.6
- Reka Flash 3
- 5.6
Coding
- Claude 2.1
- 14
- Reka Flash 3
- —
Math
- Claude 2.1
- —
- Reka Flash 3
- 33.7
Speed
- Claude 2.1
- —
- Reka Flash 3
- 87.6 t/s
TTFT
- Claude 2.1
- —
- Reka Flash 3
- 1.44 s
Input · $ / 1M tokens
- Claude 2.1
- —
- Reka Flash 3
- $0.20
Output · $ / 1M tokens
- Claude 2.1
- —
- Reka Flash 3
- $0.80
Context window
- Claude 2.1
- Best: 200K
- Reka Flash 3
- 128K
Reasoning
- Claude 2.1
- No
- Reka Flash 3
- Yes
Open weights
- Claude 2.1
- No
- Reka Flash 3
- 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 35.6 · $0.35
Not plotted for lack of data on these axes: Claude 2.1.