Published task benchmark

Code-Refactorer

Analyzes existing code for readability and duplication and suggests refactored versions.

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

Developer ToolsGenerationEvaluated 9/6/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Code-Refactorer

Analyzes existing code for readability and duplication and suggests refactored versions.

Developer ToolsPer code
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Nemotron Nano 9B v2
9B · Off-the-shelf
296 in · 1,270 out · 8.55s p50
$30.99 /100K
AWS Bedrock temporary list price
View token rates
AWS Bedrock · $0.0600 input · $0.2300 output /1M
63%
DeepSeek V3
Hosted · Off-the-shelf
286 in · 187 out · 1.48s p50
$27.21 /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
79%
GPT-5.4
Hosted · Off-the-shelf
287 in · 141 out · 1.63s p50
$283 /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
95%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small63%100/100$30.99
Qwen3 235B A22Bmid76%100/100$54.92
DeepSeek V3mid79%100/100$27.21
Mistral Large 2407mid72%100/100$76.17
Arcee Trinity Large Thinkingmid42%100/100$135
GPT-5.4frontier95%100/100$283
Claude Opus 4.7frontier84%100/100$1729
Gemini 3.1 Pro Previewfrontier56%100/100$1908
Gemma 4 E4B ITsmall59%100/100$2.71
Granite 4.1 8Bsmall55%100/100$5.17
Ministral 8B Instruct 2410small45%100/100$8.23
Qwen3 4B Instruct 2507small51%100/100$14.94

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T14:58:02.726Z.

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