Model Comparator
Compare up to four models using the same criteria.
2 models compared
- GPT-4o (May '24)
OpenAI
✓ Best published value among measured models. — Data unavailable. These metrics do not establish an overall ranking.
| Metrics | GPT-4o (May '24) OpenAI | Add a model · 2/4 | |
|---|---|---|---|
| Intelligence | 7.3 | 7.3 | |
| Coding | — | 24.2 | |
| Math | 3 | — | |
| Speed | — | 137 t/s | |
| TTFT | — | 0.93 s | |
| Input · $ / 1M tokens | — | $5 | |
| Output · $ / 1M tokens | — | $15 | |
| Context window | 128K | 128K | |
| Reasoning | No | No | |
| Open weights | Yes | No |
Intelligence
- Llama 3.1 Instruct 405B
- 7.3
- GPT-4o (May '24)
- 7.3
Coding
- Llama 3.1 Instruct 405B
- —
- GPT-4o (May '24)
- 24.2
Math
- Llama 3.1 Instruct 405B
- 3
- GPT-4o (May '24)
- —
Speed
- Llama 3.1 Instruct 405B
- —
- GPT-4o (May '24)
- 137 t/s
TTFT
- Llama 3.1 Instruct 405B
- —
- GPT-4o (May '24)
- 0.93 s
Input · $ / 1M tokens
- Llama 3.1 Instruct 405B
- —
- GPT-4o (May '24)
- $5
Output · $ / 1M tokens
- Llama 3.1 Instruct 405B
- —
- GPT-4o (May '24)
- $15
Context window
- Llama 3.1 Instruct 405B
- 128K
- GPT-4o (May '24)
- 128K
Reasoning
- Llama 3.1 Instruct 405B
- No
- GPT-4o (May '24)
- No
Open weights
- Llama 3.1 Instruct 405B
- Yes
- GPT-4o (May '24)
- No
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.
- GPT-4o (May '24)7.3 · $7.50
Not plotted for lack of data on these axes: Llama 3.1 Instruct 405B.