BasedAGIBasedAGI

Model Profile

deepseek/deepseek-r1

External Benchmark Shadowexternal_benchmark_shadowpublic
4,096 ctx

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

IQ *62%EQ *36%AccuracyCreativityBased *100%

Dimension Breakdown

IQ7 benchmarks
61.9%*
EQ3 benchmarks
35.7%*
Accuracy1 benchmark

No accuracy benchmarks found

Insufficient data
Creativity0 benchmarks

No creativity benchmarks found

Insufficient data
Based2 benchmarks
100.0%*

* 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.

Coverage Diagnostics

actively scored

Use-Case Scores

149

Total Measurements

133

Weighted Measurements

42

Weighted Sources

23

Raw Source Coverage

duckdb_nsql_leaderboard 12medhelm_leaderboard 12artifactsbenchmark_leaderboard 11crmarena_leaderboard 10languagebench 10baxbench_leaderboard 9

Weighted Source Coverage

crmarena_leaderboard 4medhelm_leaderboard 4sonar_java_quality 4languagebench 3languagebench_translation_official 3lexam_leaderboard 3

Best Use Cases for This Model

Use CaseScore
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%