Inference Latency on GAIA (General AI Assistant Reasoning)
344.1Average Latency (s)AgenticQwen-30B-A3B
Evaluation Results
| Method | Links | |
|---|---|---|
| AgenticQwen-30B-A3BHardware setup=Same as other models, Serving setup=Same as other models2026.04 | 344.1 | |
| Qwen3-30B-A3B-InstructHardware setup=Same as other models, Serving setup=Same as other models2026.04 | 355.6 | |
| Qwen3-235B-A22B-InstructHardware setup=Same as other models, Serving setup=Same as other models2026.04 | 449.5 |