Published task benchmark

Receipt-Ref

Matches receipts to calendar events to automate expense report narratives.

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

OperationsGenerationEvaluated 9/10/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Receipt-Ref

Matches receipts to calendar events to automate expense report narratives.

OperationsPer receipt
Not benchmarked
No result on this tier
Token profile pending
/100K
Run this tier to add it
Ministral 8B Instruct 2410
8B · Off-the-shelf
462 in · 161 out · 3.65s p50
$9.35 /100K
AWS Bedrock temporary proxy price
View token rates
AWS Bedrock · $0.1500 input · $0.1500 output /1M
87%
Qwen3 235B A22B
235B (22B active) · Off-the-shelf
456 in · 108 out · 1.31s p50
$40.40 /100K
Best current price · OpenRouter
Compare 2 router rates · observed 9/11/2026
OpenRouter · $0.4550 input · $1.82 output /1M
TrustedRouter · $0.6330 input · $2.11 output /1M
92%
GPT-5.4
Hosted · Off-the-shelf
411 in · 80 out · 1.75s p50
$223 /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
98%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small50%100/100$21.07
Qwen3 235B A22Bmid92%100/100$40.40
DeepSeek V3mid67%100/100$17.39
Mistral Large 2407mid92%100/100$64.94
Arcee Trinity Large Thinkingmid87%100/100$69.26
GPT-5.4frontier98%100/100$223
Claude Opus 4.7frontier95%100/100$1054
Gemini 3.1 Pro Previewfrontier94%100/100$1190
Gemma 4 E4B ITsmall62%100/100$1.35
Granite 4.1 8Bsmall79%100/100$4.53
Ministral 8B Instruct 2410small87%100/100$9.35
Qwen3 4B Instruct 2507small73%100/100$15.02

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T11:13:02.330Z.

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