Provider Snapshot
2
175.50
1340.00
Mar 26, 2026
Key Takeaways
2 cerebras models are actively benchmarked with 350 total measurements across 295 benchmark runs.
gpt-oss-120b leads the fleet with 180.00 tokens/second, while llama-3.1-8b delivers 171.00 tok/s.
Performance varies by 5.3% across the cerebras model lineup, indicating diverse optimization strategies for different use cases.
Avg time to first token across the fleet is 1340.00 ms, showing moderate responsiveness for interactive applications.
Fastest Models
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| cerebras | gpt-oss-120b | 180.00 | 1.51 | 380.00 | 1310.00 |
| cerebras | llama-3.1-8b | 171.00 | 1.54 | 353.00 | 1370.00 |
All Models
Complete list of all cerebras 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) |
|---|---|---|---|---|---|
| cerebras | gpt-oss-120b | 180.00 | 1.51 | 380.00 | 1310.00 |
| cerebras | llama-3.1-8b | 171.00 | 1.54 | 353.00 | 1370.00 |
Featured Models
Frequently Asked Questions
Based on recent tests, gpt-oss-120b shows the highest average throughput among tracked cerebras models.
This provider summary aggregates 350 individual prompts measured across 295 monitoring runs over the past month.