Provider Snapshot
18
44.17
985.56
Mar 8, 2026
Key Takeaways
18 openai models are actively benchmarked with 7152 total measurements across 6935 benchmark runs.
o3 Mini leads the fleet with 111.00 tokens/second, while gpt-4.1-mini delivers 51.60 tok/s.
Performance varies by 115.1% across the openai model lineup, indicating diverse optimization strategies for different use cases.
Avg time to first token across the fleet is 985.56 ms, showing good responsiveness for interactive applications.
The openai model fleet shows varied performance characteristics (62.1% variation coefficient), reflecting diverse model architectures.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | o3 Mini | 111.00 | 21.00 | 160.00 | 0.00 |
| openai | GPT-5.1-codex-max | 80.10 | 11.90 | 118.00 | 1390.00 |
| openai | gpt-3.5-turbo | 78.70 | 13.80 | 126.00 | 470.00 |
| openai | gpt-4.1-nano | 72.40 | 9.56 | 149.00 | 450.00 |
| openai | gpt-4o | 69.90 | 13.00 | 173.00 | 1310.00 |
| openai | gpt-4.1-mini | 51.60 | 15.20 | 84.50 | 460.00 |
All Models
Complete list of all openai models tracked in the benchmark system. Click any model name to view detailed performance data.
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| openai | 12.90 | 1.94 | 26.20 | 1830.00 | |
| openai | GPT-5.2-pro | 8.59 | 4.27 | 13.60 | 4830.00 |
| openai | GPT-5.2 | 26.80 | 9.17 | 39.90 | 910.00 |
| openai | GPT-5.1-codex-max | 80.10 | 11.90 | 118.00 | 1390.00 |
| openai | GPT-5.1-codex-mini | 25.80 | 1.38 | 54.60 | 1160.00 |
| openai | GPT-5.1-codex | 25.90 | 3.67 | 47.40 | 1290.00 |
| openai | GPT-5.1 | 30.20 | 3.73 | 56.90 | 940.00 |
| openai | o4 Mini | 49.80 | 14.50 | 75.90 | 0.00 |
| openai | o3 Mini | 111.00 | 21.00 | 160.00 | 0.00 |
| openai | gpt-4.1-nano | 72.40 | 9.56 | 149.00 | 450.00 |
| openai | gpt-4.1-mini | 51.60 | 15.20 | 84.50 | 460.00 |
| openai | gpt-4.1 | 38.60 | 6.73 | 81.20 | 500.00 |
| openai | o1-pro | 9.46 | 1.21 | 17.90 | 650.00 |
| openai | gpt-4o | 69.90 | 13.00 | 173.00 | 1310.00 |
| openai | gpt-4-turbo | 32.50 | 2.58 | 51.50 | 530.00 |
| openai | gpt-3.5-turbo | 78.70 | 13.80 | 126.00 | 470.00 |
| openai | gpt-4 | 27.90 | 3.42 | 46.40 | 660.00 |
| openai | gpt-4o-mini | 42.90 | 20.30 | 94.10 | 360.00 |
Featured Models
Frequently Asked Questions
Based on recent tests, o3 Mini shows the highest average throughput among tracked openai models.
This provider summary aggregates 7152 individual prompts measured across 6935 monitoring runs over the past month.