Published task benchmark

CSM-Summary

Sends a "here is what we discussed" email immediately after a sync call.

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

Customer SuccessSummarizationEvaluated 9/10/2026100 evaluation examplesFallback pricing checked September 11, 2026
Summarization

CSM-Summary

Sends a "here is what we discussed" email immediately after a sync call.

Customer SuccessPer call
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
591 in · 481 out · 7.73s p50
$6.32 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
99%
Cheapest
Mistral Large 2407
123B · Off-the-shelf
647 in · 508 out · 13.85s 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
100%
Best accuracy
GPT-5.4
Hosted · Off-the-shelf
542 in · 457 out · 4.29s p50
$821 /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 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small44%100/100$25.69
Qwen3 235B A22Bmid54%100/100$133
DeepSeek V3mid96%100/100$62.02
Mistral Large 2407mid100%100/100$115
Arcee Trinity Large Thinkingmid90%100/100$81.48
GPT-5.4frontier100%100/100$821
Claude Opus 4.7frontier98%100/100$2481
Gemini 3.1 Pro Previewfrontier77%100/100$2161
Gemma 4 E4B ITsmall99%100/100$6.32
Granite 4.1 8Bsmall94%100/100$7.71
Ministral 8B Instruct 2410small98%100/100$15.20
Qwen3 4B Instruct 2507small78%100/100$39.41

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T14:41:49.400Z.

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