Published task benchmark

Regex-Gen

Converts natural language descriptions into valid, tested Regular Expressions.

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

Developer ToolsGenerationEvaluated 9/5/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Regex-Gen

Converts natural language descriptions into valid, tested Regular Expressions.

Developer ToolsPer pattern
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
272 in · 1,172 out · 7.23s p50
$28.59 /100K
AWS Bedrock temporary list price
View token rates
AWS Bedrock · $0.0600 input · $0.2300 output /1M
73%
DeepSeek V3
Hosted · Off-the-shelf
227 in · 156 out · 1.78s p50
$22.31 /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
74%
GPT-5.4
Hosted · Off-the-shelf
230 in · 38 out · 1.04s p50
$115 /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
97%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small73%100/100$28.59
Qwen3 235B A22Bmid71%100/100$19.79
DeepSeek V3mid74%100/100$22.31
Mistral Large 2407mid73%100/100$64.30
Arcee Trinity Large Thinkingmid52%100/100$127
GPT-5.4frontier97%100/100$115
Claude Opus 4.7frontier86%100/100$1434
Gemini 3.1 Pro Previewfrontier86%100/100$1440
Gemma 4 E4B ITsmall69%100/100$0.9347
Granite 4.1 8Bsmall63%100/100$5.91
Ministral 8B Instruct 2410small52%100/100$6.93
Qwen3 4B Instruct 2507small52%100/100$25.63

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-05T21:57:02.547Z.

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