Published task benchmark

Briefing-Bot

Condenses 10+ articles on the same topic into a single, non-redundant briefing.

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

Document IntelligenceSummarizationEvaluated 9/6/2026100 evaluation examplesFallback pricing checked September 11, 2026
Summarization

Briefing-Bot

Condenses 10+ articles on the same topic into a single, non-redundant briefing.

Document IntelligencePer topic
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
1,115 in · 369 out · 5.68s p50
$6.25 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
83%
Cheapest
DeepSeek V3
Hosted · Off-the-shelf
1,066 in · 388 out · 6.23s p50
$72.42 /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
83%
GPT-5.4
Hosted · Off-the-shelf
1,057 in · 475 out · 4.73s p50
$977 /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
99%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small15%100/100$31.73
Qwen3 235B A22Bmid77%100/100$125
DeepSeek V3mid83%100/100$72.42
Mistral Large 2407mid74%100/100$152
Arcee Trinity Large Thinkingmid53%100/100$101
GPT-5.4frontier99%100/100$977
Claude Opus 4.7frontier91%100/100$2983
Gemini 3.1 Pro Previewfrontier49%100/100$2442
Gemma 4 E4B ITsmall83%100/100$6.25
Granite 4.1 8Bsmall67%100/100$9.40
Ministral 8B Instruct 2410small53%100/100$23.46
Qwen3 4B Instruct 2507small56%100/100$39.75

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T15:50:02.711Z.

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