Published task benchmark

Debt-Scan

Flags "TODO" comments and deprecated library usage in the codebase.

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

EngineeringAnalysisEvaluated 9/4/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Debt-Scan

Flags "TODO" comments and deprecated library usage in the codebase.

EngineeringPer repo
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
457 in · 1,327 out · 9.45s p50
$33.26 /100K
AWS Bedrock temporary list price
View token rates
AWS Bedrock · $0.0600 input · $0.2300 output /1M
63%
Mistral Large 2407
123B · Off-the-shelf
515 in · 857 out · 21.83s p50
$163 /100K
Best current price · TrustedRouter
Compare 2 router rates · observed 9/11/2026
TrustedRouter · $0.5275 input · $1.58 output /1M
OpenRouter · $2.00 input · $6.00 output /1M
83%
GPT-5.4
Hosted · Off-the-shelf
433 in · 1,020 out · 8.26s p50
$1638 /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
90%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small63%100/100$33.26
Qwen3 235B A22Bmid63%100/100$209
DeepSeek V3mid51%100/100$90.56
Mistral Large 2407mid83%100/100$163
Arcee Trinity Large Thinkingmid47%100/100$104
GPT-5.4frontier90%100/100$1638
Claude Opus 4.7frontier81%100/100$4549
Gemini 3.1 Pro Previewfrontier71%100/100$2064
Gemma 4 E4B ITsmall37%100/100$9.18
Granite 4.1 8Bsmall54%100/100$10.24
Ministral 8B Instruct 2410small45%100/100$17.98
Qwen3 4B Instruct 2507small18%100/100$80.53

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-04T22:00:02.817Z.

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