Model Profile
Kimi-K2-Instruct
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: moonshotai/Kimi-K2-Instruct
Author: moonshotai
Origin: huggingface_catalog
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 44.6%
Evidence points: 98
Raw rows: 215
Weighted rows: 19
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 247,183
Intelligence Profile
Dimension Breakdown
* Low confidence — limited benchmark evidence for this dimension
5/5 dimensions scored · Last updated Apr 21, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
BFCL Multi-turn Official
Multi Turn Acc
Normalized value 65.4% · confidence 100.0%
Strongest impact in Casual chat companion
bfcl_multiturn_official.multi_turn_acc · Apr 1, 2026
BFCL Memory Official
Memory Acc
Normalized value 51.9% · confidence 100.0%
Strongest impact in Adult ERP roleplay (explicit)
bfcl_memory_official.memory_acc · Apr 1, 2026
BFCL Relevance Detection Official
Relevance Detection
Normalized value 75.0% · confidence 100.0%
Strongest impact in Casual chat companion
bfcl_relevance_detection_official.relevance_detection · Apr 1, 2026
Galileo Agent Leaderboard v2
Avg TSQ
Normalized value 89.7% · confidence 100.0%
Strongest impact in Product positioning and messaging
galileo_agent_v2.avg_tsq · Apr 1, 2026
EQ-Bench Leaderboard
eq_bench_score
Normalized value 98.4% · confidence 100.0%
Strongest impact in Product positioning and messaging
eq_bench.eq_bench_score · Apr 1, 2026
UGI Leaderboard
Entertainment
Normalized value 89.3% · confidence 100.0%
Strongest impact in Adult ERP roleplay (explicit)
ugi_main.entertainment · Apr 1, 2026
Some fit rows have limited benchmark evidence.
2 of 12 scored use cases have low confidence or thin contributor coverage.
Coverage Diagnostics
actively scoredUse-Case Scores
58
Total Measurements
215
Weighted Measurements
19
Weighted Sources
7
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Casual chat companion use_case.companion.casual_chat | 36.3% |
| Tarot-style reading use_case.spiritual.tarot_reading | 36.3% |
| Life coaching and goal planning use_case.companion.life_coaching | 36.3% |
| Empathetic support chat use_case.companion.empathy_support_chat | 35.3% |
| Mindfulness and meditation scripts use_case.wellness.mindfulness_scripts | 35.1% |
| Adult ERP roleplay (explicit) use_case.adult.erp_roleplay | 34.6% |
| SFW roleplay and simulation use_case.creative.sfw_roleplay_simulation | 31.9% |
| Adult erotica (long-form, explicit) use_case.adult.erotica_longform | 30.8% |
| Interactive fiction / DM use_case.creative.interactive_fiction_dm | 30.7% |
| NPC dialogue use_case.gaming.npc_dialogue | 30.7% |
| Product positioning and messaging use_case.mkt.product_positioning | 18.6% |
| Campaign brief use_case.mkt.campaign_brief | 18.6% |