Published task benchmark

Forecast-Narrator

Converts a spreadsheet of financial forecast data into a plain-English executive narrative.

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

Finance & AccountingGenerationEvaluated 9/6/2026100 evaluation examplesFallback pricing checked September 11, 2026
Generation

Forecast-Narrator

Converts a spreadsheet of financial forecast data into a plain-English executive narrative.

Finance & AccountingPer forecast
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
752 in · 498 out · 7.91s p50
$6.84 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
86%
Cheapest
Mistral Large 2407
123B · Off-the-shelf
799 in · 864 out · 23.37s p50
$179 /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
77%
GPT-5.4
Hosted · Off-the-shelf
609 in · 597 out · 5.38s p50
$1048 /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 v2small13%100/100$32.91
Qwen3 235B A22Bmid11%100/100$182
DeepSeek V3mid75%100/100$68.18
Mistral Large 2407mid77%100/100$179
Arcee Trinity Large Thinkingmid31%100/100$86.98
GPT-5.4frontier99%100/100$1048
Claude Opus 4.7frontier68%100/100$3540
Gemini 3.1 Pro Previewfrontier20%100/100$2527
Gemma 4 E4B ITsmall86%100/100$6.84
Granite 4.1 8Bsmall28%100/100$11.08
Ministral 8B Instruct 2410small36%100/100$23.19
Qwen3 4B Instruct 2507small14%100/100$49.47

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T14:41:02.806Z.

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