← All models

DeepSeek-Coder-V2

open weightsdeprecated by benchmark source
DeepSeek · released 2024-06-17 · 0 offers

Context 128K tokens

Top 0 cheapest providers (Adjusted $/task)

Within the active global provider, residency and confidentiality filters.

No per-token pricing matches the active global filters.

Composite

1 of 7 inputs6 radar axes: DesignArena's two boards share one

2.7

dominance-adjusted from 5.2: a better-measured model that is at least as good on each of these inputs ranks above it

AA CodingCoding Agent v1.4AA IntelligenceAA AgenticEpoch ECISoftware ECIDesignArenaAA Intelligence: percentile 16

AA Coding Coding Agent v1.4 AA Intelligence 6.0AA Agentic Epoch ECI Software ECI DesignArena —/—

Radar: percentile among all models measured on each input; a gap means not measured.

Benchmark sheet

1 of 140 registered benchmark versions · bars show the percentile among all models measured on each benchmark.

Compare this model →

Coding

  • SciCodeno percentile3.1%

    SciCode published 2026-09-10 · Published board — A research-level scientific coding benchmark of 80 main problems (338 subproblems) across six natural-science domains, converted from real research workflows.

Reasoning

Missing coverage · 143 benchmark versions

No result does not mean a zero, or that the model was never tested. Collection failures and disputed versions retain their distinct status.

Token offers by platform · 0 offers (Adjusted $/task)

Click any underlined price to see how it is estimated and where each input comes from. How we calculate adjusted cost.

0 offers within the active global filters; “—” means the catalog is active but no public token price is available.

No token offers match the active global filters.

DeepSeek-Coder-V2 — benchmarks & cost | Benchmark Heaven