SI Index Data as of Oct 8, 2026

DeepSeek V4 Pro 0813: Price, Context, Benchmarks, and Release Details

DeepSeek provisional listing open weights · first seen Oct 8, 2026 · score computed Oct 8, 2026, 22:13 UTC
63.0
SI Score (method si-v2-absolute-shrinkage-1)
#44 of 115 ranked
69% confidence 69 percent, Medium confidence — 4 of 7 expected sources in
Coverage 55% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 65.4
Math (weight 15 percent) 77.7
Preference (weight 15 percent) —
Reasoning (weight 30 percent) 82.0

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
$0.66DeepSeek pricingOfficial off-peak uncached rate; peak is 2x; time schedule at source Retrieved Oct 8, 2026 · factual citation
Open source ↗
Output price / 1M
$1.98DeepSeek pricingOfficial off-peak uncached rate; peak is 2x; time schedule at source Retrieved Oct 8, 2026 · factual citation
Open source ↗
Context window
1Mmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Max output
384Kmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Released
Aug 12, 2026models.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Open weights
YesHugging Face HubPublic Hub repo with weight files; gating/repo upload date is not release date Retrieved Oct 8, 2026 · factual metadata; model-specific licenses
Open source ↗
License
mitHugging Face HubPublished source fact Retrieved Oct 8, 2026 · factual metadata; model-specific licenses
Open source ↗
Input modalities
textmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗

Benchmark results

35 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 92.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] deepseek-v4-pro-0813-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		92.8 reasoning
arc agi v1 public eval 95.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] deepseek-v4-pro-0813-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		95.5 reasoning
arc agi v1 public eval 93.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] deepseek-v4-pro-0813-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		93.3 reasoning
arc agi v1 semi private 87.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] deepseek-v4-pro-0813-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		87.2 reasoning
arc agi v1 semi private 90.5%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] deepseek-v4-pro-0813-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		90.5 reasoning
arc agi v1 semi private 90%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] deepseek-v4-pro-0813-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		90.0 reasoning
arc agi v2 public eval 63.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] deepseek-v4-pro-0813-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		63.6 reasoning
arc agi v2 public eval 58.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] deepseek-v4-pro-0813-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		58.9 reasoning
arc agi v2 public eval 59.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] deepseek-v4-pro-0813-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		59.4 reasoning
arc agi v2 semi private 59.7%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'high' reasoning effort. [variant] deepseek-v4-pro-0813-highPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		59.7 reasoning
arc agi v2 semi private 56.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'low' reasoning effort. [variant] deepseek-v4-pro-0813-lowPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		56.3 reasoning
arc agi v2 semi private 61.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. Evaluation conducted with 'max' reasoning effort. [variant] deepseek-v4-pro-0813-maxPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		61.3 reasoning
frontiermath tier 4 v2 26.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 19, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		26.8 math
frontiermath tiers 1 3 v2 64.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 19, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		64.6 math
gpqa diamond 91.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 18, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		91.7 reasoning
hle 42.7%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] without tools Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		42.7 reasoning
hle tools 60%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] with tools Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		60.0 reasoning
livebench coding code completion 2026_06_25 78.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		78.3 coding
livebench coding code generation 2026_06_25 76.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		76.1 coding
livebench coding javascript 2026_06_25 68.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		68.2 coding
livebench coding python 2026_06_25 50%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		50.0 coding
livebench coding typescript 2026_06_25 46.7%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		46.7 coding
livebench math amps hard 2026_06_25 98%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		98.0 math
livebench math integrals with game 2026_06_25 94%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		94.0 math
livebench math math comp 2026_06_25 97.1%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		97.1 math
livebench math olympiad 2026_06_25 91.3%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		91.3 math
livebench math simplify 2026_06_25 61.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		61.6 math
livebench reasoning connections 2026_06_25 100%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		100.0 reasoning
livebench reasoning consecutive events 2026_06_25 90.2%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		90.2 reasoning
livebench reasoning logic with navigation 2026_06_25 66%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		66.0 reasoning
livebench reasoning spatial 2026_06_25 96%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		96.0 reasoning
livebench reasoning theory of mind 2026_06_25 84.6%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		84.6 reasoning
livebench reasoning zebra puzzle 2026_06_25 96.8%LiveBenchLiveBench subtask result; dataset edition 2026_06_25; publication time is HTTP Last-Modified of the score CSV, not the dataset edition or individual evaluation date [variant] 2026_06_25Published Oct 7, 2026 Retrieved Oct 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		96.8 reasoning
otis mock aime 2024 2025 98.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 18, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		98.6 math
terminal bench v2 1 87.9%Official model cards via models.devLab-reported; metric score; transcribed by MIT models.dev catalog; not independently evaluated [variant] max effort; DeepSeek Harness minimal mode; 2.1 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		87.9 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 (4)

  • ARC Prize · arrived Oct 8, 2026
  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • Official model cards via models.dev · arrived Oct 8, 2026
  • LiveBench · arrived Oct 8, 2026

pending Awaiting (3)

  • Humanity’s Last Exam · carries 13% of expected weight
  • LMArena / Arena · carries 25% 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.