SI Index Data as of Oct 8, 2026

Claude Sonnet 5: Price, Context, Benchmarks, and Release Details

Anthropic provisional listing · first seen Oct 8, 2026 · score computed Oct 8, 2026, 22:13 UTC
67.7
SI Score (method si-v2-absolute-shrinkage-1)
#23 of 115 ranked
93% confidence 93 percent, High confidence — 5 of 7 expected sources in
Coverage 75% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 61.3
Math (weight 15 percent) 76.1
Preference (weight 15 percent) 77.1
Reasoning (weight 30 percent) 87.3

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
not yet reported
Output price / 1M
not yet reported
Context window
1Mmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Max output
128Kmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Released
Jun 30, 2026models.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Open weights
Nomodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
License
not yet reported
Input modalities
text, image, pdfmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗

Benchmark results

27 results
Benchmark Raw result Normalized (0–100) Pillar
frontiermath tier 4 v2 29.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 30, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		29.3 math
frontiermath tiers 1 3 v2 65.6%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Jun 30, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		65.6 math
gpqa diamond 80.3%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 6, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		80.3 reasoning
gpqa diamond 90.5%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Jul 1, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		90.5 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 83.1%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 ↗ 		83.1 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 60%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 ↗ 		60.0 coding
livebench coding typescript 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 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 88%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 ↗ 		88.0 math
livebench math math comp 2026_06_25 95.1%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 ↗ 		95.1 math
livebench math olympiad 2026_06_25 90.7%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 ↗ 		90.7 math
livebench math simplify 2026_06_25 60.6%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 ↗ 		60.6 math
livebench reasoning connections 2026_06_25 95.5%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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		95.5 reasoning
livebench reasoning consecutive events 2026_06_25 74.7%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 ↗ 		74.7 reasoning
livebench reasoning logic with navigation 2026_06_25 86%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 ↗ 		86.0 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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		100.0 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 8, 2026 · factual citation; Apache-2.0 code
Open source ↗ 		80.8 reasoning
livebench reasoning zebra puzzle 2026_06_25 88%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 ↗ 		88.0 reasoning
lmarena text 1442.9 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 8, 2026 · CC-BY-4.0
Open source ↗ 		77.1 preference
otis mock aime 2024 2025 80%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] maxPublished Aug 6, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		80.0 math
otis mock aime 2024 2025 94.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] xhighPublished Jul 1, 2026 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		94.7 math
swe bench pro 63.2%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Jun 30, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		63.2 coding
swe bench verified 85.2%Official model cards via models.devLab-reported; metric resolved; transcribed by MIT models.dev catalog; not independently evaluated [variant] Published Jun 30, 2026 Retrieved Oct 8, 2026 · factual citation; MIT transcription
Open source ↗ 		85.2 coding
terminal bench v2 1 80.4%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 8, 2026 · factual citation; MIT transcription
Open source ↗ 		80.4 coding
terminal bench v4 0 12.4%Terminal-BenchTerminal-Bench 4.0; published harness submission, 95% CI retained at source [variant] Claude Code; maxPublished Sep 3, 2026 Retrieved Oct 8, 2026 · Apache-2.0; factual citation
Open source ↗ 		12.4 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)

  • 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
  • Terminal-Bench · arrived Oct 8, 2026

pending Awaiting (2)

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