Model Profile
deepseek/deepseek-r1
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/deepseek/deepseek-r1
Author: deepseek
Origin: external_benchmark_shadow
Arch: unknown
Benchmark Coverage
Scored use cases: 12
Avg confidence: 35.7%
Evidence points: 255
Raw rows: 133
Weighted rows: 42
Catalog Metadata
Parameters: unknown
Context window: 4096
Downloads: 0
Price / 1M tokens: $0.27 (blended 3:1)
Intelligence Profile
Dimension Breakdown
No accuracy benchmarks found
No creativity benchmarks found
* Low confidence — limited benchmark evidence for this dimension
3/5 dimensions scored · Last updated Apr 21, 2026
Benchmark Signals
Click through to the benchmark source behind this model profile.
DuckDB NSQL Leaderboard
all_execution_accuracy
Normalized value 96.2% · confidence 100.0%
Strongest impact in Metric definition workshop
duckdb_nsql_leaderboard.all_execution_accuracy · Apr 1, 2026
DuckDB NSQL Leaderboard
hard_execution_accuracy
Normalized value 75.0% · confidence 100.0%
Strongest impact in SQL debugging
duckdb_nsql_leaderboard.hard_execution_accuracy · Apr 1, 2026
LiveSQLBench
success_rate_pct
Normalized value 61.8% · confidence 100.0%
Strongest impact in Metric definition workshop
livesqlbench.success_rate_pct · Apr 1, 2026
LEXam Leaderboard
average_score_pct
Normalized value 73.2% · confidence 100.0%
Strongest impact in Contract Drafting & Redlining
lexam_leaderboard.average_score_pct · Mar 31, 2026
Sonar Java Quality Leaderboard
functional_skill_pct
Normalized value 78.8% · confidence 100.0%
Strongest impact in Code Review Assistant
sonar_java_quality.functional_skill_pct · Apr 1, 2026
Aider Polyglot Leaderboard
percent_correct_pct
Normalized value 80.0% · confidence 100.0%
Strongest impact in Verilog/VHDL generation
aider_polyglot.percent_correct_pct · Apr 1, 2026
Coverage Diagnostics
actively scoredUse-Case Scores
149
Total Measurements
133
Weighted Measurements
42
Weighted Sources
23
Raw Source Coverage
Weighted Source Coverage
Best Use Cases for This Model
| Use Case | Score |
|---|---|
| Metric definition workshop use_case.data.metric_definition_workshop | 27.5% |
| SQL debugging use_case.data.sql_debugging | 24.7% |
| Data quality assistant use_case.data.data_quality_assistant | 23.8% |
| Code Review Assistant use_case.dev.code_review_assistant | 22.8% |
| Executive brief from metrics use_case.data.exec_brief_from_metrics | 22.5% |
| Text-to-SQL analyst assistant use_case.data.text_to_sql | 21.2% |
| Insight mining from text corpora use_case.data.insight_mining | 20.5% |
| Verilog/VHDL generation use_case.eda.verilog_generation | 20.4% |
| Legal translation use_case.legal.legal_translation | 19.3% |
| Contract Drafting & Redlining use_case.legal.contract_drafting | 19.1% |
| Integration test generation use_case.dev.integration_tests | 19.0% |
| Clause playbook check use_case.legal.playbook_clause_check | 18.5% |