Published task benchmark

Source-Verify

Cross-references footnotes in a paper against a database to ensure they are valid.

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

Document IntelligenceAnalysisEvaluated 9/10/2026100 evaluation examplesFallback pricing checked September 11, 2026
Analysis

Source-Verify

Cross-references footnotes in a paper against a database to ensure they are valid.

Document IntelligencePer paper
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
1,135 in · 1,207 out · 19.18s p50
$15.13 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
49%
Qwen3 235B A22B
235B (22B active) · Off-the-shelf
1,106 in · 1,652 out · 19.94s p50
$351 /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
54%
GPT-5.4
Hosted · Off-the-shelf
996 in · 1,657 out · 10.66s p50
$2735 /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
69%
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small31%100/100$46.24
Qwen3 235B A22Bmid54%100/100$351
DeepSeek V3mid38%100/100$139
Mistral Large 2407mid46%100/100$272
Arcee Trinity Large Thinkingmid31%100/100$165
GPT-5.4frontier69%100/100$2735
Claude Opus 4.7frontier61%100/100$5406
Gemini 3.1 Pro Previewfrontier3%100/100$2622
Gemma 4 E4B ITsmall49%100/100$15.13
Granite 4.1 8Bsmall31%100/100$14.77
Ministral 8B Instruct 2410small20%100/100$32.15
Qwen3 4B Instruct 2507small36%100/100$133

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-10T09:09:46.551Z.

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