Published task benchmark

Load-Test Breaking-Point Summary

Given time-series load-test results, identify saturation point, first failed SLA, likely bottleneck, and the evidence supporting each conclusion.

Compare measured quality, workload cost, and latency across model tiers. Results are task-specific and directional—not a general model ranking.

Engineering & ProductSummarizationEvaluated 9/9/2026100 evaluation examplesFallback pricing checked September 11, 2026
Summarization

Load-Test Breaking-Point Summary

Given time-series load-test results, identify saturation point, first failed SLA, likely bottleneck, and the evidence supporting each conclusion.

Engineering & ProductPer load test
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Gemma 4 E4B IT
E4B · Off-the-shelf
1,166 in · 412 out · 6.72s p50
$6.81 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
20%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
970 in · 386 out · 4.11s p50
$68.99 /100K
Best current price · TrustedRouter
Compare 2 router rates · observed 9/11/2026
TrustedRouter · $0.3376 input · $0.9390 output /1M
OpenRouter · $0.2900 input · $1.14 output /1M
27%
GPT-5.4
Hosted · Off-the-shelf
911 in · 735 out · 6.53s p50
$1330 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $2.50 input · $15.00 output /1M
TrustedRouter · $2.64 input · $15.82 output /1M
83%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small2%100/100$36.05
Qwen3 235B A22Bmid0%100/100$202
DeepSeek V3mid27%100/100$68.99
Mistral Large 2407mid14%100/100$189
Arcee Trinity Large Thinkingmid24%100/100$119
GPT-5.4frontier83%100/100$1330
Claude Opus 4.7frontier32%100/100$3675
Gemini 3.1 Pro Previewfrontier43%100/100$2551
Gemma 4 E4B ITsmall20%100/100$6.81
Granite 4.1 8Bsmall0%100/100$10.99
Ministral 8B Instruct 2410small2%100/100$26.97
Qwen3 4B Instruct 2507small0%100/100$67.50

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T03:07:02.611Z.

Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.

drydock

Have a neighboring workload?

Describe it in Task Explorer. If it is not measured yet, you can request a benchmark and follow future results.

Explore another task