ResearchTasksMulti-step LLM InteractionMulti-step LLM InteractionFollowBenchmarksDatasetSOTA methodSortMost resultsRecently updatedMost papersApplyDatasetSOTA methodMetricTrendResultsLast updatedDeepSeek-R1-Distill-Llama-8B Inference Performance (test)BF16100High-Precision Ratio7Feb 26, 2026Qwen3-1.7B Inference Performance (test)BF16100High-Precision Ratio7Feb 26, 2026Qwen3-4B Inference Performance (test)BF16100High-Precision Ratio7Feb 26, 2026Qwen3-8B Inference Performance (test)BF16100High-Precision Ratio7Feb 26, 2026