Generation
Source-Grounded Flashcard Generation
Given a textbook passage, generate question-answer flashcards whose answers are fully supported by the source and cover distinct concepts.
Education & EdTechPer flashcard
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
254 in · 262 out · 3.98s p50
$3.30 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
100%
Best accuracyCheapest
DeepSeek V3
Hosted · Off-the-shelf
237 in · 238 out · 1.76s p50
$30.35 /100K
Best current price · TrustedRouter
Compare 2 router rates · observed 9/11/2026
TrustedRouter · $0.3376 input · $0.9390 output /1M
OpenRouter · $0.2900 input · $1.14 output /1M
100%
Best accuracy
GPT-5.4
Hosted · Off-the-shelf
248 in · 303 out · 2.58s p50
$517 /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
| Model | Tier | Quality | Judged | Scenario cost |
|---|---|---|---|---|
| Nemotron Nano 9B v2 | small | 69% | 100/100 | $24.59 |
| Qwen3 235B A22B | mid | 72% | 100/100 | $62.43 |
| DeepSeek V3 | mid | 100% | 100/100 | $30.35 |
| Mistral Large 2407 | mid | 99% | 100/100 | $66.89 |
| Arcee Trinity Large Thinking | mid | 95% | 100/100 | $53.59 |
| GPT-5.4 | frontier | 100% | 100/100 | $517 |
| Claude Opus 4.7 | frontier | 99% | 100/100 | $1319 |
| Gemini 3.1 Pro Preview | frontier | 100% | 100/100 | $1247 |
| Gemma 4 E4B IT | small | 100% | 100/100 | $3.30 |
| Granite 4.1 8B | small | 71% | 100/100 | $4.35 |
| Ministral 8B Instruct 2410 | small | 90% | 100/100 | $7.14 |
| Qwen3 4B Instruct 2507 | small | 81% | 100/100 | $27.69 |
LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-09T09:35:02.688Z.
Directional: measured on a synthetic eval set generated by drydock. Cost/latency are not yet captured for taskrouter-run benchmarks.
drydock