BridgeBenchBridgeBench
Speed
Model Analysis

GLM 5.1

z-ai/glm-5.1

44.3

median tok/s

2353ms TTFT
100.0% success

Throughput Runs

9

TTFT Runs

6

Avg TTFT

2394ms

Avg Throughput

45.9 tok/s

Total Cost

$0.0750

Commentary

by derived

GLM 5.1 posts 44.3 tok/s median throughput with 2353ms median TTFT across 15 runs. Success rate is 100.0% with $0.08 total spend.

Factualttft

Startup latency on ttft-factual landed in the 2353ms range.

Definitionttft

Startup latency on ttft-definition landed in the 2353ms range.

Data Structuresthroughput

Sustained decode speed on throughput-data-structures contributed to the 44.3 tok/s median.

Api Designthroughput

Sustained decode speed on throughput-api-design contributed to the 44.3 tok/s median.

Essaythroughput

Sustained decode speed on throughput-essay contributed to the 44.3 tok/s median.

Notable Prompts

Data Structuresthroughput

Fastest throughput run peaked at 66.0 tok/s.

Definitionttft

Slowest startup path took 3170ms to first token.

All Runs

PromptTypeTok/sTTFT
1. Api Design
throughput-api-design
throughput60.26579ms
2. Api Design
throughput-api-design
throughput47.94573ms
3. Api Design
throughput-api-design
throughput44.34454ms
1. Data Structures
throughput-data-structures
throughput66.02245ms
2. Data Structures
throughput-data-structures
throughput52.84269ms
3. Data Structures
throughput-data-structures
throughput40.83927ms
1. Essay
throughput-essay
throughput37.35535ms
2. Essay
throughput-essay
throughput30.43911ms
3. Essay
throughput-essay
throughput33.53962ms
1. Definition
ttft-definition
ttftn/a3170ms
2. Definition
ttft-definition
ttftn/a2530ms
3. Definition
ttft-definition
ttftn/a3071ms
1. Factual
ttft-factual
ttftn/a2175ms
2. Factual
ttft-factual
ttftn/a2150ms
3. Factual
ttft-factual
ttftn/a1268ms

15 runs · Throughput rows require valid long-output runs · TTFT shown for all successful runs