SI Index Data as of Oct 9, 2026

DeepSeek V3.2: Price, Context, Benchmarks, and Release Details

DeepSeek provisional listing open weights · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:09 UTC
53.3
SI Score (method si-v3-retained-evidence-2)
#95 of 140 ranked
56% confidence 56 percent, Medium confidence — 3 of 8 expected sources in
Coverage 45% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 70.0
Math (weight 15 percent) —
Preference (weight 15 percent) 75.0
Reasoning (weight 30 percent) 31.6

Pillar weights: reasoning 30% · math 15% · coding 40% · preference 15%. Benchmark results use fixed 0–100 scales before averaging; incomplete evidence is shrunk toward 50.

Facts

Input price / 1M
$0.28LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded Retrieved Oct 9, 2026 · MIT
Open source ↗
Output price / 1M
$0.40LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: not supplied in the MIT entry; rate is a transcription, not independently verified. Exact endpoint only; cache/batch/long-context rates excluded Retrieved Oct 9, 2026 · MIT
Open source ↗
Context window
128Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
64Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Dec 1, 2025models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Open weights
Yesmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
MIT Licensemodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Input modalities
textmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

6 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 61.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] deepseek-v3.2Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		61.6 reasoning
arc agi v1 semi private 57.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] deepseek-v3.2Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		57.0 reasoning
arc agi v2 public eval 3.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] deepseek-v3.2Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		3.9 reasoning
arc agi v2 semi private 4.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] deepseek-v3.2Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		4.0 reasoning
lmarena text 1420.1 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		75.0 preference
swe bench verified 70%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; high; 2.0.0Published Feb 17, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		70.0 coding

Normalization uses fixed absolute 0–100 scales for each unit, independently of other models that have a result on each benchmark. Coverage and evidence breadth still affect the composite; compare the evaluation conditions before reading a small score gap as decisive. “lab-reported” marks the provider's own published figure.

Sources: in and pending

in Reported (3)

  • ARC Prize · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026
  • SWE-bench Verified · arrived Oct 8, 2026

pending Awaiting (5)

  • Epoch AI Benchmarking · carries 23% of expected weight
  • Humanity’s Last Exam · carries 11% of expected weight
  • Official model cards via models.dev · carries 4% of expected weight
  • LiveBench · carries 11% of expected weight
  • Terminal-Bench · carries 6% of expected weight

The confidence % rises as pending sources publish. Some sources never cover some models — that is why 100% confidence arrives at 80% of expected weight, not at full coverage.