Hermes 3 70B - NC Bench

nousresearch/hermes-3-llama-3.1-70b

Hermes 3 70B

via OpenRouter

Release Date

Aug 15th, 2024

Context Size

128k

Reasoning

Benchmark Cost

$1.08

Speed

28.9 tok/s

Subcategories

Bad Writing Habits

Detects common prose quality anti-patterns in AI-generated creative writing, including passive voice, past progressive overuse, weak dialogue tags, filter words, purple prose, cliches, AI-ism words/adverbs/names, and more.

Scenario	#1	#2	#3	#4	#5	Total
Detailed Writing Rules
Fantasy: entering an ancient ruin Creative Writing Hallucination	85	82	79	78	73	79%
Horror: alone in an eerie place at night Creative Writing Hallucination	81	80	80	73	70	77%
Literary fiction: old friends reunite Creative Writing Hallucination	86	84	80	72	67	78%
Mystery: examining a crime scene Creative Writing Hallucination	95	91	82	80	75	85%
Romance: separated couple reunites Creative Writing Hallucination	87	85	84	83	76	83%
Thriller: chase through city streets Creative Writing Hallucination	85	85	84	78	76	82%
Detailed Writing Rules						80.54%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	81	73	72	71	68	73%
Horror: alone in an eerie place at night Creative Writing Hallucination	91	85	74	69	69	78%
Literary fiction: old friends reunite Creative Writing Hallucination	79	79	75	73	71	75%
Mystery: examining a crime scene Creative Writing Hallucination	84	82	71	71	69	75%
Romance: separated couple reunites Creative Writing Hallucination	81	80	80	74	65	76%
Thriller: chase through city streets Creative Writing Hallucination	86	85	79	76	72	80%
genre						76.14%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	75	74	71	70	70	72%
Horror: alone in an eerie place at night Creative Writing Hallucination	89	85	85	71	65	79%
Literary fiction: old friends reunite Creative Writing Hallucination	89	83	79	73	73	79%
Mystery: examining a crime scene Creative Writing Hallucination	81	80	79	75	75	78%
Romance: separated couple reunites Creative Writing Hallucination	82	79	78	75	71	77%
Thriller: chase through city streets Creative Writing Hallucination	84	79	78	76	72	78%
Novelcrafter Default Prompt						77.12%
77.93%

Codex Extraction

Evaluates a model's ability to extract structured codex entries (characters, locations, objects, lore) from prose passages and return them as well-formed XML.

Scenario	#1	#2	#3	#4	#5	Total
Long: The Spire of Echoes (Dense) Tooling Reasoning	92	90	90	90	81	89%
Medium: The Hollow (Inferred) Tooling Reasoning	90	89	88	87	86	88%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	89	85	84	84	75	83%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	97	95	92	89	85	92%
87.92%

Codex Red Herring (False Positive Detection)

Tests whether models correctly report "no violations" when a codex is fully consistent with the prose passage. Models that hallucinate false violations (false positives) fail. Uses a 2×2 matrix of text length × codex size, with bare and detailed-entry variants.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
basic entries
Long text (~1594 words), big codex (51 entries) Hallucination	100	50	13	7	6	6	5	5	4	4	20%
Long text (~1594 words), small codex (11 entries) Hallucination	100	100	100	100	100	100	42	33	7	6	69%
Short text (~524 words), big codex (51 entries) Hallucination	100	100	100	100	100	42	38	35	8	7	63%
Short text (~524 words), small codex (11 entries) Hallucination	100	100	100	50	42	38	33	13	7	5	49%
basic entries											50.09%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	100	30	10	8	8	7	6	5	5	4	18%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	100	100	100	50	50	50	38	33	32	8	56%
Short text (~524 words), big codex (51 detailed entries) Hallucination	50	38	33	32	32	13	13	10	8	8	24%
Short text (~524 words), small codex (11 detailed entries) Hallucination	100	100	100	50	31	25	17	13	10	6	45%
detailed entries											35.80%
42.95%

Codex Violation Detection

Detects factual inconsistencies between a story bible and prose passages. The model must output structured XML identifying each violation with paragraph number and substring.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
matrix
Large codex (40 entries), long passage (1,019 words) Tooling Reasoning	64	64	61	60	55	53	51	50	38	0	49%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	75	69	69	67	61	57	54	50	46	0	55%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	76	73	72	70	67	66	66	62	47	0	60%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	93	88	87	87	87	84	83	76	70	0	76%
matrix											59.90%
tiers
5 codex entries Tooling Reasoning	76	75	75	66	60	57	57	50	44	0	56%
10 codex entries Tooling Reasoning	86	81	79	79	79	72	72	72	58	33	71%
20 codex entries Tooling Reasoning	79	71	69	69	69	60	59	44	33	0	55%
40 codex entries Tooling Reasoning	80	70	67	62	61	61	60	53	52	51	62%
tiers											61.05%
60.48%

Data extraction

Extract key details from a given block of text.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
All valid emails Utility	100	100	100	100	100	100	100	100	100	100	100%
Contextual pronoun Utility	100	100	100	100	100	100	100	100	100	100	100%
Fruits excluding citrus Utility	100	100	100	100	100	100	100	100	100	100	100%
Future event time Reasoning	50	50	50	50	50	50	50	50	50	50	50%
Guess the pet Reasoning	100	100	100	100	100	100	100	100	100	100	100%
Highest-rated movie Reasoning	100	100	100	100	100	100	100	100	100	100	100%
Indirect birth year Reasoning	100	100	100	100	100	100	100	100	100	100	100%
What instrument does Lucy play? Reasoning	100	100	100	100	100	100	100	100	100	100	100%
What's the color of the car? Utility	100	100	100	100	100	100	100	100	100	100	100%
What's the correct time? Reasoning	100	0	0	0	0	0	0	0	0	0	10%
Who's the sister? Reasoning	100	100	100	100	100	100	100	100	100	100	100%
Who's the tallest? Reasoning	100	100	100	100	100	100	100	100	100	50	95%
87.92%

Dialogue tags

Various tasks related to dialogue tags in text.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
dialogue-200
Write 200 words with 10% dialogue Rule Following Utility	75	50	48	43	14	3	1	0	0	0	23%
Write 200 words with 50% dialogue Rule Following Utility	100	64	58	54	52	47	42	25	10	2	45%
Write 200 words with 90% dialogue Rule Following Utility	78	67	64	50	50	48	28	27	2	0	41%
dialogue-200											36.71%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	43	41	31	1	0	0	0	0	0	0	12%
Write 500 words with 50% dialogue Rule Following Utility	81	63	35	22	13	0	0	0	0	0	21%
Write 500 words with 70% dialogue Rule Following Utility	45	39	23	8	4	3	2	1	0	0	13%
dialogue-500											15.21%
Ungrouped
Write unattributed dialogue Rule Following	100	100	100	100	100	61	61	14	14	1	65%
31.53%

Language Comprehension

Does the model understand more than just English?

Scenario	#1	#2	#3	#4	#5	Total
Asking for directions (Dutch) Language	100	0	0	0	0	20%
Asking for directions (German) Language	100	100	100	100	0	80%
Friend got new kittens (German) Language	100	100	100	100	100	100%
Friend got new kittens (Tagalog) Language	100	100	100	100	100	100%
75.00%

Language Writing

Can the model generate text in different languages?

Scenario	#1	#2	#3	#4	#5	Total
Character dialogue (French) in a story Language	100	100	100	100	100	100%
Character dialogue (German) in a story Language	100	100	100	60	0	72%
Character dialogue (Hindi) in a story Language	100	100	100	71	60	86%
Character dialogue (Italian) in a story Language	100	100	100	91	58	90%
Character dialogue (Spanish) in a story Language	100	100	100	88	80	94%
88.33%

N-Length Sentences

Write sentences with exactly N words

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
Write sentences with 5 words each Utility	100	100	98	92	90	87	87	69	58	56	84%
Write sentences with 10 words each Utility	81	57	42	41	40	36	30	8	7	6	35%
Write sentences with 20 words each Utility	27	16	15	8	7	6	0	0	0	0	8%
42.10%

Novel outline

Handle questions about the outline of a novel in various formats

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
outline-count
Count acts Utility	100	100	100	100	100	100	100	100	100	100	100%
Count chapters Utility	100	100	100	100	100	100	100	100	100	100	100%
Count scenes Utility	100	0	0	0	0	0	0	0	0	0	10%
outline-count											70.00%
pov-count
Count point of views for Jack and Olivia Utility	100	100	100	100	100	50	0	0	0	0	55%
Count point of views for Jack Harper Utility	100	100	0	0	0	0	0	0	0	0	20%
Count point of views for Olivia Utility	100	100	0	0	0	0	0	0	0	0	20%
pov-count											31.67%
50.83%

Text Replacement

Tests deterministic text transformations: renaming characters/locations, expanding contractions, tense rewriting, POV shifts, gender swaps, combined transformations, and word avoidance. Scored by checking each expected change independently.

Scenario	#1	#2	#3	#4	#5	#6	#7	Total
Generic Prompt
Avoid said/asked/replied/answered Text Editing	100	100	100	100	100	100	100	100%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	100	100	100	100	100	100	100	100%
Combined: 3rd person past → 1st person present Text Editing	99	99	99	99	99	99	98	99%
Expand all contractions Text Editing	100	100	100	100	100	100	100	100%
Location rename: market square, outer ring, bridge, northern mines Text Editing	100	100	100	100	96	96	96	98%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	100	100	74	74	74	74	74	81%
Passive voice → active voice Text Editing Hallucination	89	82	81	81	79	78	59	78%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	99	99	87	98%
Tense rewriting: past to present Text Editing	97	96	96	96	93	93	92	95%
Generic Prompt								94.30%
Specific Prompt
Avoid said/asked/replied/answered Text Editing	100	100	100	100	100	100	36	91%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	100	100	100	100	100	0	0	71%
Combined: 3rd person past → 1st person present Text Editing	90	5	0	0	0	0	0	14%
Expand all contractions Text Editing	100	0	0	0	0	0	0	14%
Location rename: market square, outer ring, bridge, northern mines Text Editing	100	100	100	54	0	0	0	51%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	100	100	100	52	0	0	0	50%
Passive voice → active voice Text Editing Hallucination	92	91	0	0	0	0	0	26%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	33	33	33	2	0	43%
Tense rewriting: past to present Text Editing	100	100	100	0	0	0	0	43%
Specific Prompt								44.79%
69.55%

Tool usage within Novelcrafter

Output messages that are related to tool usage within Novelcrafter

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
Create alternate prose sections Tooling	100	100	100	100	100	100	100	100	100	100	100%
100.00%

Voice/dialogue sheets

Extract dialogue from given text as voice sheets.

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
Multiple speakers Rule Following	0	0	0	0	0	0	0	0	0	0	0%
Simple Rule Following	100	100	100	100	100	100	0	0	0	0	60%
Simple (1-shot) 1-shot Rule Following	100	100	100	100	100	100	100	100	100	100	100%
Simple (5-shot) Few-shot Rule Following	100	100	100	100	100	100	100	100	100	100	100%
Unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	0	0	80%
68.00%

Write N of X

Write exactly N words/sentences/paragraphs...

Scenario	#1	#2	#3	#4	#5	#6	#7	#8	#9	#10	Total
paragraphs
1 paragraph summary Utility	100	100	100	100	100	100	100	100	100	100	100%
3 paragraph summary Utility	100	100	100	100	100	100	100	0	0	0	70%
5 paragraph summary Utility	100	100	100	0	0	0	0	0	0	0	30%
paragraphs											66.67%
sentences
1 sentence summary Utility	100	100	100	100	100	100	100	100	100	100	100%
3 sentence summary Utility	100	100	100	100	100	100	100	100	100	100	100%
10 sentence summary Utility	100	100	100	100	92	92	77	54	54	27	80%
20 sentence summary Utility	100	9	2	0	0	0	0	0	0	0	11%
50 sentence summary Utility	0	0	0	0	0	0	0	0	0	0	0%
sentences											58.14%
words
10 word summary Utility	100	98	98	92	92	0	0	0	0	0	48%
20 word summary Utility	77	54	0	0	0	0	0	0	0	0	13%
50 word summary Utility	0	0	0	0	0	0	0	0	0	0	0%
100 word summary Utility	100	100	54	0	0	0	0	0	0	0	25%
200 word summary Utility	0	0	0	0	0	0	0	0	0	0	0%
words											17.32%
44.41%