7 Modelle

Nous Research-Modelle: Intelligenz, Leistung und Preis

Name: Artificial Analysis Intelligence Index
Creator: Artificial Analysis
License: https://artificialanalysis.ai/docs/legal/Terms-of-Use.pdf

Nous Research

Intelligenz

Updated

Hermes 4 70B (non-reasoning)

Hermes 4 70B

Hermes 4 405B

DeepHermes 3 - Mistral 24B (non-reasoning)

DeepHermes 3 - Llama-3.1 8B (non-reasoning)

Artificial Analysis Intelligence Index

Zeit pro Aufgabe

Hermes 4 70B (non-reasoning)

Hermes 4 70B

Hermes 4 405B

DeepHermes 3 - Mistral 24B (non-reasoning)

DeepHermes 3 - Llama-3.1 8B (non-reasoning)

Pro Aufgabe des Intelligence Index

Kosten

Hermes 4 70B (non-reasoning)

Hermes 4 70B

Hermes 4 405B

DeepHermes 3 - Mistral 24B (non-reasoning)

DeepHermes 3 - Llama-3.1 8B (non-reasoning)

Pro Aufgabe des Intelligence Index

Artificial Analysis hat 7 Modelle von Nous Research gebenchmarkt. Unten werden die wichtigsten Kennzahlen dieser Modelle verglichen.

Bei der Latenz bietet Hermes 4 - Llama-3.1 405B (Non-reasoning) mit 5,25 s die kürzeste Zeit bis zum ersten Antworttoken.

IntelligenzUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v5.0.1 incorporates 9 evaluations: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), and Terminal-Bench-Science 0.1

No data available

Artificial Analysis Intelligence Index v5.0.1 includes: AA-Briefcase v1.1, AutomationBench-AA, Terminal-Bench 4.0, FrontierCode 2.0, AA-Omniscience v1.1, GDP.pdf, HLE-Diamond, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1. See Intelligence Index methodology for further details, including a breakdown of each evaluation and how we run them.

Intelligence Index vs. Kosten pro Aufgabe

Artificial Analysis Intelligence Index · Weighted average cost (USD) per Artificial Analysis Intelligence Index task

Most attractive quadrant

No data available

Weighted average cost per Intelligence Index task. Each evaluation’s cost is calculated from input, cache hit, cache write, reasoning, and answer token prices, divided by task count, and weighted by its Intelligence Index weight.

Kosten

Kosten pro Aufgabe des Intelligence Index

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

No data available

Geschwindigkeit und Latenz

Zeit pro Aufgabe des Intelligence Index

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Speed at the model's own endpoint or the median across providers · Lower is better

No data available

The weighted average time (minutes) per Artificial Analysis Intelligence Index task: output tokens per task divided by output speed, weighted by each benchmark's weight in the Intelligence Index.

Speed and latency metrics average each endpoint's runs over the past 5 days, and the error rate pools them. We run the benchmark every 6 hours, and endpoints of deprecated models every 18 hours.

Fähigkeitswerte

Fähigkeitsindizes

Misst die Leistung von Modellen bei bestimmten Fähigkeiten und in bestimmten Branchen

Finance & Accounting Index

Incorporates 5 evaluations: AA-Briefcase v1.1, AA-Omniscience v1.1, HLE-Diamond, AutomationBench-AA, GDP.pdf · Higher is better

No data available

Strategy & Ops Index

Incorporates 4 evaluations: AutomationBench-AA, AA-Briefcase v1.1, AA-Omniscience v1.1, GDP.pdf · Higher is better

No data available

Legal Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf, AutomationBench-AA · Higher is better

No data available

Healthcare & Medical Index

Incorporates 5 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, MLCR-AA, AutomationBench-AA, HLE-Diamond · Higher is better

No data available

Engineering Index

Incorporates 7 evaluations: AA-Omniscience v1.1, CritPt v2 (Hard Subset), Terminal-Bench-Science 0.1, HLE-Diamond, Terminal-Bench 4.0, FrontierCode 2.0, AA-Briefcase v1.1 · Higher is better

No data available

Economics Index

Incorporates 4 evaluations: AA-Omniscience v1.1, AA-Briefcase v1.1, HLE-Diamond, GDP.pdf · Higher is better

No data available

Alle Veröffentlichungen von Nous Research

Weitere Details

								Gewichte		Anbieter-Benchmarks
Hermes 3 - Llama-3.1 70B	Nous Research	-	70.6B	128k	0,7 $	-	102	🤗		Anzeigen
Hermes 4 - Llama-3.1 70B (Non-reasoning)	Nous Research	-	70.6B	128k	-	-	-	🤗	-	Anzeigen
Hermes 4 - Llama-3.1 70B (Reasoning)	Nous Research	-	70.6B	128k	-	-	-	🤗	-	Anzeigen
Hermes 4 - Llama-3.1 405B (Reasoning)	Nous Research	-	406B	128k	1,2 $	-	22	🤗		Anzeigen
DeepHermes 3 - Mistral 24B Preview (Non-reasoning)	Nous Research	-	24B	32k	-	-	-	🤗	-	Anzeigen
DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)	Nous Research	-	8B	128k	-	-	-	🤗	-	Anzeigen
Hermes 4 - Llama-3.1 405B (Non-reasoning)	Nous Research	-	406B	128k	1,2 $	-	22	🤗		Anzeigen

Nous Research-Modelle: Intelligenz, Leistung und Preis

Intelligenz

Zeit pro Aufgabe

Kosten

IntelligenzUpdated

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index

Intelligence Index vs. Kosten pro Aufgabe

Cost per Intelligence Index Task

Artificial Analysis Intelligence Index

Kosten

Kosten pro Aufgabe des Intelligence Index

Cost per Intelligence Index Task

Geschwindigkeit und Latenz

Zeit pro Aufgabe des Intelligence Index

Time per Intelligence Index Task

Time Period

Fähigkeitswerte

Fähigkeitsindizes

Alle Veröffentlichungen von Nous Research

Weitere Details