Published task benchmark

Environmental Impact Report Synthesizer

Summarize key pollutants and mitigation measures from an Environmental Impact Report.

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

Legal & ComplianceSummarizationEvaluated 9/4/2026100 evaluation examplesFallback pricing checked September 11, 2026
Summarization

Environmental Impact Report Synthesizer

Summarize key pollutants and mitigation measures from an Environmental Impact Report.

Legal & CompliancePer report
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
308 in · 741 out · 11.53s p50
$8.47 /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
369 in · 728 out · 19.30s p50
$135 /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
93%
Best accuracy
GPT-5.4
Hosted · Off-the-shelf
300 in · 1,535 out · 18.03s p50
$2378 /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
93%
Best accuracy
All 12 model results and methodology

Generated 100/100 examples

ModelTierQualityJudgedScenario cost
Nemotron Nano 9B v2small67%100/100$35.77
Qwen3 235B A22Bmid84%100/100$244
DeepSeek V3mid85%100/100$93.49
Mistral Large 2407mid93%100/100$135
Arcee Trinity Large Thinkingmid80%100/100$96.98
GPT-5.4frontier93%100/100$2378
Claude Opus 4.7frontier93%100/100$4526
Gemini 3.1 Pro Previewfrontier18%100/100$2429
Gemma 4 E4B ITsmall86%100/100$8.47
Granite 4.1 8Bsmall59%100/100$9.61
Ministral 8B Instruct 2410small54%100/100$14.60
Qwen3 4B Instruct 2507small46%100/100$99.68

LLM-judge pass rate on 100 synthetic examples. Generator: gpt-5.2. Judge: gpt-5.2. Evaluated 2026-09-04T13:13:02.510Z.

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