Model Profile
Llama 3.3 70B 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: external/meta/llama-3-3-70b-instruct
Author: meta
Origin: external_benchmark_shadow
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 48.5%
Evidence points: 141
Raw rows: 227
Weighted rows: 28
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 0
Intelligence Profile
Dimension Breakdown
* Low confidence — limited benchmark evidence for this dimension
5/5 dimensions scored · Last updated Apr 14, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
BFCL Relevance Detection Official
Relevance Detection
Normalized value 100.0% · 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
Normalized value 27.8% · confidence 100.0%
Strongest impact in Casual chat companion
bfcl_multiturn_official.multi_turn_acc · Apr 1, 2026
BigCodeBench Official
bigcodebench_complete_pct
Normalized value 91.0% · confidence 100.0%
Strongest impact in Verilog/VHDL generation
bigcodebench_official.bigcodebench_complete_pct · Apr 1, 2026
BFCL Memory Official
Memory Acc
Normalized value 14.6% · confidence 100.0%
Strongest impact in Adult ERP roleplay (explicit)
bfcl_memory_official.memory_acc · Apr 1, 2026
BigCodeBench Official
bigcodebench_instruct_pct
Normalized value 90.5% · confidence 100.0%
Strongest impact in Integration test generation
bigcodebench_official.bigcodebench_instruct_pct · Apr 1, 2026
BFCL Relevance Detection Official
Irrelevance Detection
Normalized value 50.4% · confidence 100.0%
Strongest impact in Casual chat companion
bfcl_relevance_detection_official.irrelevance_detection · 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
133
Total Measurements
227
Weighted Measurements
28
Weighted Sources
11
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Casual chat companion use_case.companion.casual_chat | 22.4% |
| Life coaching and goal planning use_case.companion.life_coaching | 22.4% |
| Tarot-style reading use_case.spiritual.tarot_reading | 22.4% |
| Empathetic support chat use_case.companion.empathy_support_chat | 21.7% |
| Mindfulness and meditation scripts use_case.wellness.mindfulness_scripts | 21.6% |
| Adult ERP roleplay (explicit) use_case.adult.erp_roleplay | 19.7% |
| SFW roleplay and simulation use_case.creative.sfw_roleplay_simulation | 18.6% |
| NPC dialogue use_case.gaming.npc_dialogue | 17.9% |
| Interactive fiction / DM use_case.creative.interactive_fiction_dm | 17.9% |
| Adult erotica (long-form, explicit) use_case.adult.erotica_longform | 17.3% |
| Integration test generation use_case.dev.integration_tests | 12.2% |
| Verilog/VHDL generation use_case.eda.verilog_generation | 11.6% |