Cohere Command R+ (Aug. 2024)

cohere/command-r-plus-08-2024

Cohere Command R+ (Aug. 2024)

via OpenRouter

Release Date

Aug 31st, 2024

Context Size

128k

Reasoning

Benchmark Cost

$11.09

Speed

39.3 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	76	75	74	71	67	73%
Horror: alone in an eerie place at night Creative Writing Hallucination	80	79	78	75	70	77%
Literary fiction: old friends reunite Creative Writing Hallucination	82	75	74	74	73	76%
Mystery: examining a crime scene Creative Writing Hallucination	85	80	79	76	73	79%
Romance: separated couple reunites Creative Writing Hallucination	89	85	80	80	72	82%
Thriller: chase through city streets Creative Writing Hallucination	84	81	81	80	77	80%
Detailed Writing Rules						77.59%
genre
Fantasy: entering an ancient ruin Creative Writing Hallucination	79	73	72	70	68	72%
Horror: alone in an eerie place at night Creative Writing Hallucination	80	79	74	73	69	75%
Literary fiction: old friends reunite Creative Writing Hallucination	80	77	77	74	72	76%
Mystery: examining a crime scene Creative Writing Hallucination	84	84	79	75	71	79%
Romance: separated couple reunites Creative Writing Hallucination	81	81	78	78	75	79%
Thriller: chase through city streets Creative Writing Hallucination	81	78	77	76	75	77%
genre						76.31%
Novelcrafter Default Prompt
Fantasy: entering an ancient ruin Creative Writing Hallucination	79	78	73	72	69	74%
Horror: alone in an eerie place at night Creative Writing Hallucination	82	81	81	80	80	81%
Literary fiction: old friends reunite Creative Writing Hallucination	89	84	82	73	73	80%
Mystery: examining a crime scene Creative Writing Hallucination	94	92	88	86	83	89%
Romance: separated couple reunites Creative Writing Hallucination	84	79	79	73	72	77%
Thriller: chase through city streets Creative Writing Hallucination	83	82	77	76	71	78%
Novelcrafter Default Prompt						79.91%
77.94%

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	90	90	87	86	86	88%
Medium: The Hollow (Inferred) Tooling Reasoning	87	85	82	81	79	83%
Medium: Through the Thornveil (Scattered) Tooling Reasoning	89	84	83	80	60	79%
Short: The Rusty Lantern (Explicit) Tooling Reasoning	91	91	90	86	76	87%
84.23%

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	17	17	10	8	8	7	7	5	5	18%
Long text (~1594 words), small codex (11 entries) Hallucination	100	17	17	10	10	10	8	7	6	1	19%
Short text (~524 words), big codex (51 entries) Hallucination	100	100	100	100	100	100	25	13	10	5	65%
Short text (~524 words), small codex (11 entries) Hallucination	100	100	100	100	100	100	25	10	8	8	65%
basic entries											41.83%
detailed entries
Long text (~1594 words), big codex (51 detailed entries) Hallucination	100	100	100	100	100	17	13	13	3	1	55%
Long text (~1594 words), small codex (11 detailed entries) Hallucination	100	100	100	100	100	100	17	13	13	10	65%
Short text (~524 words), big codex (51 detailed entries) Hallucination	100	100	100	100	100	100	100	17	17	1	73%
Short text (~524 words), small codex (11 detailed entries) Hallucination	100	100	100	100	100	100	100	100	10	8	82%
detailed entries											68.74%
55.29%

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	55	55	54	51	49	49	42	42	3	3	40%
Large codex (40 entries), short passage (165 words) Tooling Reasoning	74	70	69	68	66	63	52	49	44	0	56%
Small codex (7 entries), long passage (734 words) Tooling Reasoning	80	76	75	72	70	66	0	0	0	0	44%
Small codex (7 entries), short passage (165 words) Tooling Reasoning	97	97	93	90	90	90	87	84	80	79	89%
matrix											57.10%
tiers
5 codex entries Tooling Reasoning	93	87	87	76	75	67	57	57	57	44	70%
10 codex entries Tooling Reasoning	89	89	86	79	79	66	64	61	49	33	70%
20 codex entries Tooling Reasoning	88	82	77	77	73	70	66	65	60	55	71%
40 codex entries Tooling Reasoning	66	66	60	60	60	48	44	41	40	33	52%
tiers											65.66%
61.38%

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	50	50	50	50	50	50	50	50	60%
Fruits excluding citrus Utility	100	100	100	100	0	0	0	0	0	0	40%
Future event time Reasoning	100	100	100	100	100	50	50	50	50	50	75%
Guess the pet Reasoning	100	100	100	50	50	50	50	50	50	50	65%
Highest-rated movie Reasoning	100	100	100	100	100	100	100	100	50	50	90%
Indirect birth year Reasoning	0	0	0	0	0	0	0	0	0	0	0%
What instrument does Lucy play? Reasoning	100	100	100	100	100	50	50	50	50	50	75%
What's the color of the car? Utility	100	100	100	100	100	100	100	50	50	50	85%
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	50	50	50	50	50	75%
Who's the tallest? Reasoning	100	100	100	100	100	100	100	50	50	50	85%
63.33%

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	14	2	0	0	0	0	0	0	0	0	2%
Write 200 words with 50% dialogue Rule Following Utility	71	50	50	49	46	42	36	2	0	0	35%
Write 200 words with 90% dialogue Rule Following Utility	31	14	10	1	0	0	0	0	0	0	6%
dialogue-200											13.91%
dialogue-500
Write 500 words with 30% dialogue Rule Following Utility	48	47	22	0	0	0	0	0	0	0	12%
Write 500 words with 50% dialogue Rule Following Utility	88	78	38	2	1	0	0	0	0	0	21%
Write 500 words with 70% dialogue Rule Following Utility	82	50	49	44	29	18	12	5	2	0	29%
dialogue-500											20.52%
Ungrouped
Write unattributed dialogue Rule Following	100	100	100	100	100	100	100	100	61	14	87%
27.24%

Language Comprehension

Does the model understand more than just English?

Scenario	#1	#2	#3	#4	#5	Total
Asking for directions (Dutch) Language	100	100	0	0	0	40%
Asking for directions (German) Language	100	100	100	100	100	100%
Friend got new kittens (German) Language	0	0	0	0	0	0%
Friend got new kittens (Tagalog) Language	100	100	100	100	100	100%
60.00%

Language Writing

Can the model generate text in different languages?

Scenario	#1	#2	#3	#4	#5	Total
Character dialogue (French) in a story Language	92	70	65	63	50	68%
Character dialogue (German) in a story Language	86	75	70	62	50	68%
Character dialogue (Hindi) in a story Language	100	100	88	55	0	68%
Character dialogue (Italian) in a story Language	100	100	78	70	60	82%
Character dialogue (Spanish) in a story Language	100	100	90	55	53	80%
73.15%

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	94	89	82	78	76	76	65	53	51	36	70%
Write sentences with 10 words each Utility	95	84	81	70	70	59	56	56	18	10	60%
Write sentences with 20 words each Utility	25	19	0	0	0	0	0	0	0	0	4%
44.79%

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	50	50	50	50	50	50	0	0	0	40%
Count point of views for Jack Harper Utility	0	0	0	0	0	0	0	0	0	0	0%
Count point of views for Olivia Utility	100	0	0	0	0	0	0	0	0	0	10%
pov-count											16.67%
43.33%

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	81	81	78	78	78	78	67	77%
Character rename: Elena->Mirabel, Gregor->Aldric Text Editing	100	100	49	47	40	38	33	58%
Combined: 3rd person past → 1st person present Text Editing	96	27	25	22	18	11	3	29%
Expand all contractions Text Editing	57	48	33	32	32	29	18	36%
Location rename: market square, outer ring, bridge, northern mines Text Editing	92	79	71	58	49	47	42	63%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	74	74	74	74	74	74	65	72%
Passive voice → active voice Text Editing Hallucination	40	29	27	27	27	23	22	28%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	95	52	49	49	43	40	37	52%
Tense rewriting: past to present Text Editing	99	97	96	93	85	68	60	85%
Generic Prompt								55.59%
Specific Prompt
Avoid said/asked/replied/answered Text Editing	91	86	83	81	67	66	65	77%
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	98	98	98	98%
Expand all contractions Text Editing	100	100	100	99	99	99	98	99%
Location rename: market square, outer ring, bridge, northern mines Text Editing	100	100	100	100	100	100	100	100%
Multi-character gender swap: Priya(F)->Rohan(M), Mara unchanged Text Editing	100	100	100	100	100	99	99	100%
Passive voice → active voice Text Editing Hallucination	78	76	71	54	53	50	46	61%
POV shift: 3rd person to 1st person (Elena's perspective) Text Editing	100	100	100	100	100	100	93	99%
Tense rewriting: past to present Text Editing	100	99	97	93	86	86	82	92%
Specific Prompt								91.86%
73.72%

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	0	90%
90.00%

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	100	100	0	0	0	0	0	0	0	0	20%
Simple Rule Following	100	100	100	100	100	100	100	100	0	0	80%
Simple (1-shot) 1-shot Rule Following	100	100	100	100	100	100	100	100	100	0	90%
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	0	0	0	0	60%
70.00%

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	100	100	0	90%
5 paragraph summary Utility	100	100	100	100	100	100	100	100	0	0	80%
paragraphs											90.00%
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	98	98	98	98	98	92	92	77	77	93%
20 sentence summary Utility	77	9	2	2	0	0	0	0	0	0	9%
50 sentence summary Utility	0	0	0	0	0	0	0	0	0	0	0%
sentences											60.43%
words
10 word summary Utility	100	100	100	100	100	100	100	100	100	98	100%
20 word summary Utility	100	98	98	98	98	92	77	77	77	77	90%
50 word summary Utility	0	0	0	0	0	0	0	0	0	0	0%
100 word summary Utility	92	77	54	54	27	9	9	0	0	0	32%
200 word summary Utility	27	0	0	0	0	0	0	0	0	0	3%
words											44.86%
61.27%