LLM Benchmark Report
Generated: __TIMESTAMP__ · __TOTAL_TESTS__ tests completed
__EMPTY_STATE__
__MODEL_META__
__WINNER__
__AVG_GEN_TPS__
Avg Gen t/s
Std: __GEN_STD__ · Range: [__MIN_GEN__, __MAX_GEN__]
__MED_GEN_TPS__
Median Gen t/s
__AVG_PROMPT_TPS__
Avg Prompt t/s
Std: __PROMPT_STD__ · Range: [__MIN_PROMPT__, __MAX_PROMPT__]
__MED_PROMPT_TPS__
Median Prompt t/s
__AVG_LATENCY__
Avg Latency/token
Std: __LAT_STD__ · Range: [__MIN_LAT__, __MAX_LAT__]
__MED_LATENCY__
Median Latency
__AVG_FT__
Avg First Token
Std: __FT_STD__ · Range: [__MIN_FT__, __MAX_FT__]
__BEST_GEN__
Best Gen t/s
__IMPACT_HTML__
Performance Comparison (Top __TOP_N__)
Latency vs Throughput
All Results (click row to expand details)