SI Index Data as of Oct 9, 2026

Claude Sonnet 4.6: Price, Context, Benchmarks, and Release Details

Anthropic provisional listing · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:50 UTC
68.3
SI Score (method si-v3-retained-evidence-2)
#20 of 140 ranked
100% confidence 100 percent, Full confidence — 5 of 7 expected sources in
Coverage 81% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 60.6
Math (weight 15 percent) 81.9
Preference (weight 15 percent) 78.4
Reasoning (weight 30 percent) 80.9

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
$3.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗
Output price / 1M
$15.00Anthropic API pricingOfficial Claude API base tokens; lowest short-context global Standard rate; cache, batch, fast and regional premiums excluded Retrieved Oct 9, 2026 · factual citation
Open source ↗
Context window
1Mmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
64Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Feb 17, 2026models.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Open weights
Nomodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, image, pdfmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗

Benchmark results

37 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 95.3%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 a 120K thinking budget and a maximum context window of 128K tokens and 'high' output effort. [variant] claude_sonnet_4_6_highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		95.3 reasoning
arc agi v1 public eval 95.8%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 a 120K thinking budget and a maximum context window of 128K tokens and 'max' output effort. [variant] claude_sonnet_4_6_maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		95.8 reasoning
arc agi v1 semi private 86.5%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 a 120K thinking budget and a maximum context window of 128K tokens and 'high' output effort. [variant] claude_sonnet_4_6_highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		86.5 reasoning
arc agi v1 semi private 86%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 a 120K thinking budget and a maximum context window of 128K tokens and 'max' output effort. [variant] claude_sonnet_4_6_maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		86.0 reasoning
arc agi v2 public eval 65.7%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 a 120K thinking budget and a maximum context window of 128K tokens and 'high' output effort. [variant] claude_sonnet_4_6_highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		65.7 reasoning
arc agi v2 public eval 62.4%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 a 120K thinking budget and a maximum context window of 128K tokens and 'max' output effort. [variant] claude_sonnet_4_6_maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		62.4 reasoning
arc agi v2 semi private 60.4%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 a 120K thinking budget and a maximum context window of 128K tokens and 'high' output effort. [variant] claude_sonnet_4_6_highPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		60.4 reasoning
arc agi v2 semi private 58.3%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 a 120K thinking budget and a maximum context window of 128K tokens and 'max' output effort. [variant] claude_sonnet_4_6_maxPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		58.3 reasoning
gpqa diamond 87.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished Feb 20, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		87.4 reasoning
gpqa diamond 83.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		83.3 reasoning
gpqa diamond 78.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		78.8 reasoning
gpqa diamond 83.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		83.3 reasoning
hle 34.6%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] no toolsPublished Jun 30, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		34.6 reasoning
hle tools 46.8%Official model cards via models.devLab-reported; metric accuracy; transcribed by MIT models.dev catalog; not independently evaluated [variant] with toolsPublished Jun 30, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		46.8 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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		78.3 coding
livebench coding code generation 2026_06_25 80.3%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 ↗ 		80.3 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 76%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 ↗ 		76.0 math
livebench math integrals with game 2026_06_25 90%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 ↗ 		90.0 math
livebench math math comp 2026_06_25 94.1%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 ↗ 		94.1 math
livebench math olympiad 2026_06_25 87.9%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 ↗ 		87.9 math
livebench math simplify 2026_06_25 62.9%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 ↗ 		62.9 math
livebench reasoning connections 2026_06_25 99.3%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 ↗ 		99.3 reasoning
livebench reasoning consecutive events 2026_06_25 92.7%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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		92.7 reasoning
livebench reasoning logic with navigation 2026_06_25 70%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 ↗ 		70.0 reasoning
livebench reasoning spatial 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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		100.0 reasoning
livebench reasoning theory of mind 2026_06_25 73.1%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 ↗ 		73.1 reasoning
livebench reasoning zebra puzzle 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 9, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		96.0 reasoning
lmarena text 1457.8 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 9, 2026 · CC-BY-4.0
Open source ↗ 		78.4 preference
otis mock aime 2024 2025 85.8%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] 32KPublished Feb 20, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		85.8 math
otis mock aime 2024 2025 75.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] highPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		75.6 math
otis mock aime 2024 2025 71.1%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 6, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		71.1 math
otis mock aime 2024 2025 82.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] mediumPublished Jul 13, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		82.2 math
swe bench verified 75.2%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published Feb 21, 2026 Retrieved Oct 9, 2026 · CC-BY
Open source ↗ 		75.2 coding
terminal bench v2 1 67%Official model cards via models.devLab-reported; metric success rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Terminus-2; 2.1Published Jun 30, 2026 Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		67.0 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 (5)

  • 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
  • LMArena / Arena · arrived Oct 8, 2026

pending Awaiting (2)

  • 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.