Published task benchmark

Release-Logs

Generates "What's New" logs for developers from GitHub commit history.

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

EngineeringGenerationEvaluated 9/4/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Release-Logs

Generates "What's New" logs for developers from GitHub commit history.

EngineeringPer release
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
468 in · 204 out · 2.97s p50
$3.14 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
77%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
434 in · 164 out · 1.48s p50
$30.05 /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
86%
Best accuracy
GPT-5.4
Hosted · Off-the-shelf
422 in · 180 out · 2.08s p50
$376 /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
86%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small15%100/100$31.88
Qwen3 235B A22Bmid53%100/100$59.42
DeepSeek V3mid86%100/100$30.05
Mistral Large 2407mid79%100/100$83.08
Arcee Trinity Large Thinkingmid48%100/100$104
GPT-5.4frontier86%100/100$376
Claude Opus 4.7frontier71%100/100$1399
Gemini 3.1 Pro Previewfrontier85%100/100$1768
Gemma 4 E4B ITsmall77%100/100$3.14
Granite 4.1 8Bsmall43%100/100$7.00
Ministral 8B Instruct 2410small62%100/100$11.76
Qwen3 4B Instruct 2507small44%100/100$23.64

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-04T22:11:02.358Z.

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