BasedAGIBasedAGI
Menu

Model Profile

DeepSeek-Coder-V2-Instruct

4,096 ctxOpen weights

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: deepseek-ai/DeepSeek-Coder-V2-Instruct

Author: deepseek-ai

Origin: huggingface_catalog

Arch: unknown

Benchmark Coverage

Scored use cases: 1

Avg confidence: 10.1%

Evidence points: 3

Raw rows: 23

Weighted rows: 3

Catalog Metadata

Parameters: unknown

Context window: 4096

Downloads: 5,798

Intelligence Profile

IQ *66%EQ—Accuracy—Creativity—Based—

Dimension Breakdown

IQ1 benchmark
65.7%*
EQ0 benchmarks

No eq benchmarks found

Insufficient data
Accuracy0 benchmarks

No accuracy benchmarks found

Insufficient data
Creativity0 benchmarks

No creativity benchmarks found

Insufficient data
Based0 benchmarks

No based benchmarks found

Insufficient data

* Low confidence — limited benchmark evidence for this dimension

1/5 dimensions scored · Last updated Apr 14, 2026

Benchmark Signals

Click through to the benchmark source behind this model profile.

BigCodeBench Official

bigcodebench_complete_pct

2.1%

Normalized value 95.0% · confidence 100.0%

Strongest impact in Verilog/VHDL generation

bigcodebench_official.bigcodebench_complete_pct · Apr 1, 2026

BigCodeBench Official

bigcodebench_instruct_pct

1.5%

Normalized value 93.4% · confidence 100.0%

Strongest impact in Verilog/VHDL generation

bigcodebench_official.bigcodebench_instruct_pct · Apr 1, 2026

BigCodeBench Official

bigcodebench_hard_complete_pct

1.0%

Normalized value 72.4% · confidence 100.0%

Strongest impact in Verilog/VHDL generation

bigcodebench_official.bigcodebench_hard_complete_pct · Apr 1, 2026

Some fit rows have limited benchmark evidence.

1 of 1 scored use cases have low confidence or thin contributor coverage.

Coverage Diagnostics

actively scored

Use-Case Scores

1

Total Measurements

23

Weighted Measurements

3

Weighted Sources

1

Raw Source Coverage

mmlu_pro_leaderboard 15bigcodebench_official 8

Weighted Source Coverage

bigcodebench_official 3

Best Use Cases for This Model

Use CaseScore
Verilog/VHDL generation

use_case.eda.verilog_generation

8.9%