SI Index Data as of Oct 9, 2026

DeepSeek-R1: Price, Context, Benchmarks, and Release Details

DeepSeek provisional listing open weights · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:47 UTC
47.9
SI Score (method si-v3-retained-evidence-2)
#111 of 140 ranked
88% confidence 88 percent, High confidence — 5 of 8 expected sources in
Coverage 70% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 44.5
Math (weight 15 percent) 86.6
Preference (weight 15 percent) 70.3
Reasoning (weight 30 percent) 18.9

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
$0.55LiteLLMFirst-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
$2.19LiteLLMFirst-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
32.8Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Jan 20, 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
not yet reported
Input modalities
textmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

13 results
Benchmark Raw result Normalized (0–100) Pillar
aider polyglot 71.4%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished Jun 6, 2025 Retrieved Oct 9, 2026 · Apache-2.0
Open source ↗ 		71.4 coding
arc agi v1 public eval 27.0%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_r1_0528-openrouterPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		27.0 reasoning
arc agi v1 semi private 21.2%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_r1_0528-openrouterPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		21.2 reasoning
arc agi v1 semi private 15.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] R1Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		15.8 reasoning
arc agi v2 public eval 0.3%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_r1_0528-openrouterPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		0.3 reasoning
arc agi v2 public eval 0.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] R1Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		0.3 reasoning
arc agi v2 semi private 1.1%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_r1_0528-openrouterPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		1.1 reasoning
arc agi v2 semi private 1.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] R1Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		1.3 reasoning
gpqa diamond 76.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		76.3 reasoning
lmarena text 1372.7 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		70.3 preference
math level 5 96.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		96.6 math
otis mock aime 2024 2025 66.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 29, 2025 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		66.4 math
terminal bench 6.1%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Mar 11, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		6.1 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 (5)

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

pending Awaiting (3)

  • Humanity’s Last Exam · carries 12% of expected weight
  • LiveBench · carries 12% 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.