SI Index Data as of Oct 9, 2026

DeepSeek-V3: Price, Context, Benchmarks, and Release Details

DeepSeek provisional listing open weights · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:50 UTC
54.1
SI Score (method si-v3-retained-evidence-2)
#92 of 140 ranked
93% confidence 93 percent, High confidence — 2 of 4 expected sources in
Coverage 75% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) —
Math (weight 15 percent) 48.5
Preference (weight 15 percent) 66.0
Reasoning (weight 30 percent) 56.5

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
$0.27LiteLLMFirst-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
$1.10LiteLLMFirst-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
131Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
8.2Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Dec 26, 2024models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Open weights
Yesmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
DeepSeek Model 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

4 results
Benchmark Raw result Normalized (0–100) Pillar
gpqa diamond 56.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jan 27, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		56.5 reasoning
lmarena text 1332.5 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		66.0 preference
math level 5 64.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Jan 27, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		64.9 math
otis mock aime 2024 2025 15.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 25, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		15.8 math

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 (2)

  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026

pending Awaiting (2)

  • Official model cards via models.dev · carries 7% of expected weight
  • LiveBench · carries 19% 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.