Published task benchmark

Spreadsheet Formula Repair Agent

Find broken or inconsistent formulas and restore the intended pattern.

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

Office and knowledge-work automationAnalysisEvaluated 9/11/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Spreadsheet Formula Repair Agent

Find broken or inconsistent formulas and restore the intended pattern.

Office and knowledge-work automationPer spreadsheet
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
600 in · 757 out · 11.34s p50
$9.25 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
91%
Cheapest
Mistral Large 2407
123B · Off-the-shelf
648 in · 762 out · 20.35s p50
$155 /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
526 in · 494 out · 4.82s p50
$873 /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 v2small51%100/100$34.85
Qwen3 235B A22Bmid84%100/100$240
DeepSeek V3mid85%100/100$78.85
Mistral Large 2407mid92%100/100$155
Arcee Trinity Large Thinkingmid52%100/100$137
GPT-5.4frontier99%100/100$873
Claude Opus 4.7frontier94%100/100$3178
Gemini 3.1 Pro Previewfrontier94%100/100$1330
Gemma 4 E4B ITsmall91%100/100$9.25
Granite 4.1 8Bsmall70%100/100$11.61
Ministral 8B Instruct 2410small67%100/100$18.95
Qwen3 4B Instruct 2507small63%100/100$109

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-11T12:33:02.334Z.

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