Model Comparator
Compare up to four models using the same criteria.
2 models compared
- Claude 3 Haiku
Anthropic
- Reka Flash 3
Reka AI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | Claude 3 Haiku Anthropic | Reka Flash 3 Reka AI | Add a model · 2/4 |
|---|---|---|---|
| Intelligence | 5.6 | 5.6 | |
| Math | — | 33.7 | |
| Speed | — | 87.6 t/s | |
| TTFT | — | 1.44 s | |
| Input · $ / 1M tokens | $0.25×1.3 relative to the lowest price among the compared models | Best: $0.20 | |
| Output · $ / 1M tokens | $1.25×1.6 relative to the lowest price among the compared models | Best: $0.80 | |
| Context window | Best: 200K | 128K | |
| Reasoning | No | Yes | |
| Open weights | No | Yes |
Intelligence
- Claude 3 Haiku
- 5.6
- Reka Flash 3
- 5.6
Math
- Claude 3 Haiku
- —
- Reka Flash 3
- 33.7
Speed
- Claude 3 Haiku
- —
- Reka Flash 3
- 87.6 t/s
TTFT
- Claude 3 Haiku
- —
- Reka Flash 3
- 1.44 s
Input · $ / 1M tokens
- Claude 3 Haiku
- $0.25×1.3 relative to the lowest price among the compared models
- Reka Flash 3
- Best: $0.20
Output · $ / 1M tokens
- Claude 3 Haiku
- $1.25×1.6 relative to the lowest price among the compared models
- Reka Flash 3
- Best: $0.80
Context window
- Claude 3 Haiku
- Best: 200K
- Reka Flash 3
- 128K
Reasoning
- Claude 3 Haiku
- No
- Reka Flash 3
- Yes
Open weights
- Claude 3 Haiku
- 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.
- Claude 3 Haiku5.6 · $0.50
- Reka Flash 35.6 · $0.35