Published task benchmark

Research-Synth

Synthesizes multiple web research sources into a structured digest with key findings and gaps.

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

OperationsResearchEvaluated 9/6/2026100 evaluation examplesFallback pricing checked September 11, 2026
Research

Research-Synth

Synthesizes multiple web research sources into a structured digest with key findings and gaps.

OperationsPer query
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
529 in · 610 out · 9.43s p50
$7.55 /100K
Current price · TrustedRouter
View token rates · observed 9/11/2026
TrustedRouter · $0.0211 input · $0.1055 output /1M
75%
Cheapest
Mistral Large 2407
123B · Off-the-shelf
598 in · 803 out · 20.89s p50
$159 /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
55%
GPT-5.4
Hosted · Off-the-shelf
501 in · 997 out · 8.19s p50
$1621 /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
95%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small6%100/100$33.67
Qwen3 235B A22Bmid24%100/100$158
DeepSeek V3mid44%100/100$74.11
Mistral Large 2407mid55%100/100$159
Arcee Trinity Large Thinkingmid7%100/100$98.50
GPT-5.4frontier95%100/100$1621
Claude Opus 4.7frontier70%100/100$3772
Gemini 3.1 Pro Previewfrontier37%100/100$2380
Gemma 4 E4B ITsmall75%100/100$7.55
Granite 4.1 8Bsmall24%100/100$10.79
Ministral 8B Instruct 2410small32%100/100$17.55
Qwen3 4B Instruct 2507small16%100/100$48.30

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-06T14:23:02.804Z.

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