SI Index Data as of Oct 9, 2026

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

DeepSeek provisional listing open weights · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:09 UTC
63.1
SI Score (method si-v3-retained-evidence-2)
#45 of 140 ranked
85% confidence 85 percent, High confidence — 4 of 7 expected sources in
Coverage 68% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 58.1
Math (weight 15 percent) 67.5
Preference (weight 15 percent) 77.8
Reasoning (weight 30 percent) 80.3

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
$1.32LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded Retrieved Oct 9, 2026 · MIT
Open source ↗
Output price / 1M
$3.96LiteLLMFirst-party API Standard token rate; MIT LiteLLM transcription. Provider documentation: https://api-docs.deepseek.com/quick_start/pricing. Exact endpoint only; cache/batch/long-context rates excluded Retrieved Oct 9, 2026 · MIT
Open source ↗
Context window
1Mmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
384Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Apr 24, 2026models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Open weights
Yesmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
textmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

33 results
Benchmark Raw result Normalized (0–100) Pillar
frontiermath tier 4 v2 2.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 17, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		2.4 math
frontiermath tiers 1 3 v2 45.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 17, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		45.3 math
gpqa diamond 90.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		90.9 reasoning
gpqa diamond 89.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 16, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		89.6 reasoning
gpqa diamond 73.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		73.2 reasoning
gpqa diamond 90.1%Official model cards via models.devLab-reported; metric pass@1; transcribed by MIT models.dev catalog; not independently evaluated [variant] preview checkpoint; max effort Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		90.1 reasoning
hle 37.7%Official model cards via models.devLab-reported; metric pass@1; transcribed by MIT models.dev catalog; not independently evaluated [variant] preview checkpoint; max effort; without tools Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		37.7 reasoning
hle tools 48.2%Official model cards via models.devLab-reported; metric pass@1; transcribed by MIT models.dev catalog; not independently evaluated [variant] preview checkpoint; max effort; with tools Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		48.2 reasoning
livebench coding code completion 2026_06_25 69.6%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		69.6 coding
livebench coding code generation 2026_06_25 70.4%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		70.4 coding
livebench coding javascript 2026_06_25 54.5%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		54.5 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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		50.0 coding
livebench coding typescript 2026_06_25 23.3%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		23.3 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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		98.0 math
livebench math integrals with game 2026_06_25 78%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		78.0 math
livebench math math comp 2026_06_25 96.1%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		96.1 math
livebench math olympiad 2026_06_25 90.6%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		90.6 math
livebench math simplify 2026_06_25 55.9%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		55.9 math
livebench reasoning connections 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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		98.0 reasoning
livebench reasoning consecutive events 2026_06_25 75.4%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		75.4 reasoning
livebench reasoning logic with navigation 2026_06_25 64%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		64.0 reasoning
livebench reasoning spatial 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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		94.0 reasoning
livebench reasoning theory of mind 2026_06_25 80.8%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		80.8 reasoning
livebench reasoning zebra puzzle 2026_06_25 92%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		92.0 reasoning
lmarena text 1451.0 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		77.8 preference
mmlu pro 87.5%Official model cards via models.devLab-reported; metric EM; transcribed by MIT models.dev catalog; not independently evaluated [variant] preview checkpoint; max effort Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		87.5 reasoning
otis mock aime 2024 2025 95.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		95.6 math
otis mock aime 2024 2025 96.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 17, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		96.7 math
otis mock aime 2024 2025 46.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] nonePublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		46.7 math
swe bench pro 55.4%Official model cards via models.devLab-reported; metric resolved; transcribed by MIT models.dev catalog; not independently evaluated [variant] preview checkpoint; max effort Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		55.4 coding
swe bench verified 77.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 18, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		77.6 coding
swe bench verified 80.6%Official model cards via models.devLab-reported; metric resolved; transcribed by MIT models.dev catalog; not independently evaluated [variant] Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		80.6 coding
terminal bench v2 0 67.9%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] preview checkpoint; max effort; 2.0 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		67.9 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)

  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • Official model cards via models.dev · arrived Oct 8, 2026
  • LiveBench · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026

pending Awaiting (3)

  • ARC Prize · carries 13% of expected weight
  • Humanity’s Last Exam · carries 13% 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.