Published task benchmark

PR-Summarizer

Summarizes a pull request diff into a structured review: what changed, why it matters, and risks.

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

Developer ToolsSummarizationEvaluated 9/6/202698 evaluation examplesFallback pricing checked September 11, 2026
Summarization

PR-Summarizer

Summarizes a pull request diff into a structured review: what changed, why it matters, and risks.

Developer ToolsPer pull request
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
901 in · 334 out · 5.45s p50
$5.42 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
87%
Cheapest
Mistral Large 2407
123B · Off-the-shelf
952 in · 407 out · 10.81s p50
$115 /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
92%
GPT-5.4
Hosted · Off-the-shelf
746 in · 413 out · 3.76s p50
$806 /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
100%
Best accuracy
All 12 model results and methodology

Generated 98/100 examples — partial set accepted at the success threshold

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small29%98/98$24.64
Qwen3 235B A22Bmid27%98/98$122
DeepSeek V3mid87%98/98$59.46
Mistral Large 2407mid92%98/98$115
Arcee Trinity Large Thinkingmid66%98/98$96.56
GPT-5.4frontier100%98/98$806
Claude Opus 4.7frontier67%98/98$3539
Gemini 3.1 Pro Previewfrontier100%98/98$1848
Gemma 4 E4B ITsmall87%98/98$5.42
Granite 4.1 8Bsmall52%98/98$9.65
Ministral 8B Instruct 2410small53%98/98$17.55
Qwen3 4B Instruct 2507small19%98/98$41.10

LLM-judge pass rate on 98 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T16:07:02.521Z.

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