Published task benchmark

Zero-Downtime Schema Migration Planning

Given a current schema, target schema, traffic pattern, and deployment constraints, order expand-migrate-contract steps and flag unsafe operations.

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

Engineering & ProductGenerationEvaluated 9/9/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Zero-Downtime Schema Migration Planning

Given a current schema, target schema, traffic pattern, and deployment constraints, order expand-migrate-contract steps and flag unsafe operations.

Engineering & ProductPer schema
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
429 in · 1,256 out · 20.57s p50
$14.16 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
17%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
394 in · 1,133 out · 11.30s p50
$120 /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
13%
GPT-5.4
Hosted · Off-the-shelf
384 in · 1,610 out · 16.32s p50
$2511 /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
91%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small0%100/100$48.25
Qwen3 235B A22Bmid10%100/100$281
DeepSeek V3mid13%100/100$120
Mistral Large 2407mid6%100/100$175
Arcee Trinity Large Thinkingmid1%100/100$159
GPT-5.4frontier91%100/100$2511
Claude Opus 4.7frontier10%100/100$5339
Gemini 3.1 Pro Previewfrontier3%100/100$2459
Gemma 4 E4B ITsmall17%100/100$14.16
Granite 4.1 8Bsmall1%100/100$14.45
Ministral 8B Instruct 2410small0%100/100$19.45
Qwen3 4B Instruct 2507small0%100/100$114

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T02:35:02.507Z.

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