Generation

Given a math skill, difficulty, and student interest, generate solvable word problems with verified answers and no irrelevant assumptions.

Education & EdTechPer word problem

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

151 in · 454 out · 5.28s p50

$5.11 /100K

Current price · TrustedRouter

View token rates · observed 9/11/2026

TrustedRouter · $0.0211 input · $0.1055 output /1M

54%

Cheapest

Qwen3 235B A22B

235B (22B active) · Off-the-shelf

146 in · 606 out · 5.27s p50

$117 /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

64%

GPT-5.4

Hosted · Off-the-shelf

143 in · 348 out · 3.73s p50

$558 /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

88%

Best accuracy

All 12 model results and methodology

Generated 100/100 examples

Model	Tier	Quality	Judged	Scenario cost
Nemotron Nano 9B v2	small	47%	100/100	$31.22
Qwen3 235B A22B	mid	64%	100/100	$117
DeepSeek V3	mid	64%	100/100	$45.20
Mistral Large 2407	mid	49%	100/100	$89.62
Arcee Trinity Large Thinking	mid	35%	100/100	$114
GPT-5.4	frontier	88%	100/100	$558
Claude Opus 4.7	frontier	81%	100/100	$2011
Gemini 3.1 Pro Preview	frontier	57%	100/100	$2058
Gemma 4 E4B IT	small	54%	100/100	$5.11
Granite 4.1 8B	small	46%	100/100	$7.86
Ministral 8B Instruct 2410	small	14%	100/100	$8.98
Qwen3 4B Instruct 2507	small	42%	100/100	$39.15

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T09:13:02.523Z.

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?