Model Profile

Arch-Agent-3B

Name: Arch-Agent-3B
Rating: 1.7 (44 reviews)
Author: katanemo

4,096 ctxOpen weights

Use this page to decide where this model is a strong fit. Rankings below are benchmark-backed by use case, with explicit confidence and contributor metrics.

Identity

ID: katanemo/Arch-Agent-3B

Author: katanemo

Origin: huggingface_catalog

Arch: unknown

Benchmark Coverage

Scored use cases: 11

Avg confidence: 35.3%

Evidence points: 44

Raw rows: 83

Weighted rows: 4

Catalog Metadata

Parameters: unknown

Context window: 4096

Downloads: 27

Intelligence Profile

Dimension Breakdown

IQ0 benchmarks

No iq benchmarks found

Insufficient data

EQ8 benchmarks

30.1%*

Accuracy3 benchmarks

40.7%*

Creativity0 benchmarks

No creativity benchmarks found

Insufficient data

Based0 benchmarks

No based benchmarks found

Insufficient data

* Low confidence — limited benchmark evidence for this dimension

2/5 dimensions scored · Last updated Apr 21, 2026

Benchmark Signals

Click through to the benchmark source behind this model profile.

BFCL Relevance Detection Official

Relevance Detection

5.1%

Normalized value 68.8% · confidence 100.0%

Strongest impact in Casual chat companion

bfcl_relevance_detection_official.relevance_detection · Apr 1, 2026

BFCL Multi-turn Official

Multi Turn Acc

4.3%

Normalized value 45.1% · confidence 100.0%

Strongest impact in Casual chat companion

bfcl_multiturn_official.multi_turn_acc · Apr 1, 2026

BFCL Relevance Detection Official

Irrelevance Detection

2.2%

Normalized value 73.0% · confidence 100.0%

Strongest impact in Casual chat companion

bfcl_relevance_detection_official.irrelevance_detection · Apr 1, 2026

BFCL Memory Official

Memory Acc

1.4%

Normalized value 12.3% · confidence 100.0%

Strongest impact in Adult ERP roleplay (explicit)

bfcl_memory_official.memory_acc · Apr 1, 2026

Some fit rows have limited benchmark evidence.

1 of 11 scored use cases have low confidence or thin contributor coverage.

Coverage Diagnostics

actively scored

Use-Case Scores

Total Measurements

Weighted Measurements

Weighted Sources

Raw Source Coverage

bfcl_adjacent_public 30bfcl_overall 30toolace_api_heavy_benchmark 12bfcl_multiturn_official 5bfcl_memory_official 4bfcl_relevance_detection_official 2

Weighted Source Coverage

bfcl_relevance_detection_official 2bfcl_memory_official 1bfcl_multiturn_official 1

Best Use Cases for This Model

Use Case	Vertical	Score	Confidence	Evidence	Top Contributor
Casual chat companion use_case.companion.casual_chat	companion	17.0%	41.2%	4	BFCL Relevance Detection Official: Relevance Detection
Tarot-style reading use_case.spiritual.tarot_reading	companion	17.0%	41.2%	4	BFCL Relevance Detection Official: Relevance Detection
Life coaching and goal planning use_case.companion.life_coaching	companion	17.0%	41.2%	4	BFCL Relevance Detection Official: Relevance Detection
Empathetic support chat use_case.companion.empathy_support_chat	companion	16.5%	40.0%	4	BFCL Relevance Detection Official: Relevance Detection
Mindfulness and meditation scripts use_case.wellness.mindfulness_scripts	companion	16.5%	39.8%	4	BFCL Relevance Detection Official: Relevance Detection
Adult ERP roleplay (explicit) use_case.adult.erp_roleplay	adult	13.5%	36.3%	4	BFCL Multi-turn Official: Multi Turn Acc
SFW roleplay and simulation use_case.creative.sfw_roleplay_simulation	creative	13.1%	34.3%	4	BFCL Multi-turn Official: Multi Turn Acc
Interactive fiction / DM use_case.creative.interactive_fiction_dm	creative	12.7%	33.1%	4	BFCL Multi-turn Official: Multi Turn Acc
NPC dialogue use_case.gaming.npc_dialogue	creative	12.7%	33.1%	4	BFCL Multi-turn Official: Multi Turn Acc
Adult erotica (long-form, explicit) use_case.adult.erotica_longform	adult	12.5%	33.0%	4	BFCL Multi-turn Official: Multi Turn Acc
Language conversation partner use_case.lang.conversation_partner	education	6.0%	15.1%	4	BFCL Relevance Detection Official: Relevance Detection