Model Profile
Claude-3.5-Sonnet
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/anthropic/claude-3-5-sonnet
Author: anthropic
Origin: external_benchmark_shadow
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 29.4%
Evidence points: 175
Raw rows: 140
Weighted rows: 28
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 0
Price / 1M tokens: $6.00 (blended 3:1)
Intelligence Profile
Dimension Breakdown
No creativity benchmarks found
No based benchmarks found
* Low confidence — limited benchmark evidence for this dimension
3/5 dimensions scored · Last updated Apr 14, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
DuckDB NSQL Leaderboard
all_execution_accuracy
Normalized value 86.5% · confidence 100.0%
Strongest impact in Executive brief from metrics
duckdb_nsql_leaderboard.all_execution_accuracy · Apr 1, 2026
LanguageBench Translation Official (Split)
translation_to:bleu
Normalized value 81.7% · confidence 100.0%
Strongest impact in Archaic and historical translation
languagebench_translation_official.translation_to_bleu · Apr 1, 2026
LanguageBench
overall:mean
Normalized value 97.4% · confidence 100.0%
Strongest impact in Archaic and historical translation
languagebench.overall_mean · Apr 1, 2026
LanguageBench Grammar/Clarity Official (Split)
grammar_clarity_score_pct
Normalized value 90.6% · confidence 100.0%
Strongest impact in Translation and localization
languagebench_grammar_clarity_official.grammar_clarity_score_pct · Apr 1, 2026
MedHELM
average_score_pct
Normalized value 65.7% · confidence 100.0%
Strongest impact in Patient-friendly explanations
medhelm_leaderboard.average_score_pct · Apr 1, 2026
OpenVLM OCRBench Official
ocrbench_score_pct
Normalized value 82.9% · confidence 100.0%
Strongest impact in Grammar and writing coach
openvlm_ocrbench_official.ocrbench_score_pct · Apr 1, 2026
Some fit rows have limited benchmark evidence.
1 of 12 scored use cases have low confidence or thin contributor coverage.
Coverage Diagnostics
actively scoredUse-Case Scores
100
Total Measurements
140
Weighted Measurements
28
Weighted Sources
15
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Archaic and historical translation use_case.history.archaic_translation | 27.2% |
| Brand voice localization use_case.mkt.brand_voice_localization | 25.1% |
| Legal translation use_case.legal.legal_translation | 21.8% |
| Patient-friendly explanations use_case.health.patient_friendly_summaries | 21.0% |
| Grammar and writing coach use_case.lang.grammar_coach | 20.6% |
| Translation and localization use_case.business.translation_localization | 20.1% |
| Multilingual Customer Support use_case.cx.multilingual_support | 19.8% |
| Historical document summarization use_case.history.historical_doc_summarization | 19.4% |
| Language conversation partner use_case.lang.conversation_partner | 18.9% |
| Executive brief from metrics use_case.data.exec_brief_from_metrics | 18.6% |
| Patient education bot (RAG grounded) use_case.health.patient_education_bot | 17.6% |
| Tail spend categorization use_case.proc.tail_spend_categorization | 17.3% |