SI Index Data as of Oct 8, 2026

Claude Sonnet 4: Price, Context, Benchmarks, and Release Details

Anthropic provisional listing · first seen Oct 8, 2026 · score computed Oct 8, 2026, 22:13 UTC
45.2
SI Score (method si-v2-absolute-shrinkage-1)
#101 of 115 ranked
96% confidence 96 percent, High confidence — 4 of 7 expected sources in
Coverage 76% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 43.8
Math (weight 15 percent) 65.9
Preference (weight 15 percent) 66.7
Reasoning (weight 30 percent) 21.2

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
200Kmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Max output
64Kmodels.devPublished source fact Retrieved Oct 8, 2026 · MIT
Open source ↗
Released
May 22, 2025models.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

25 results
Benchmark Raw result Normalized (0–100) Pillar
aider polyglot 56.4%Aider polyglotPublished source fact [variant] Aider polyglot; 225 cases; 2 attemptsPublished May 24, 2025 Retrieved Oct 8, 2026 · Apache-2.0
Open source ↗ 		56.4 coding
arc agi v1 public eval 33%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514Published Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		33.0 reasoning
arc agi v1 public eval 56.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-16k-bedrockPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		56.8 reasoning
arc agi v1 public eval 31.3%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-1kPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		31.3 reasoning
arc agi v1 public eval 48.6%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-8k-bedrockPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		48.6 reasoning
arc agi v1 semi private 23.8%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514Published Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		23.8 reasoning
arc agi v1 semi private 40%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-16k-bedrockPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		40.0 reasoning
arc agi v1 semi private 28.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-1kPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		28.0 reasoning
arc agi v1 semi private 29.0%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-8k-bedrockPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		29.0 reasoning
arc agi v2 public eval 2.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514Published Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		2.1 reasoning
arc agi v2 public eval 4.4%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-16k-bedrockPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		4.4 reasoning
arc agi v2 public eval 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] claude-sonnet-4-20250514-thinking-1kPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		1.3 reasoning
arc agi v2 public eval 2.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-8k-bedrockPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		2.9 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] claude-sonnet-4-20250514Published Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		1.3 reasoning
arc agi v2 semi private 5.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-16k-bedrockPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		5.9 reasoning
arc agi v2 semi private 0.9%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-1kPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		0.9 reasoning
arc agi v2 semi private 2.1%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-sonnet-4-20250514-thinking-8k-bedrockPublished Oct 6, 2026 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		2.1 reasoning
gpqa diamond 66.7%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 22, 2025 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		66.7 reasoning
hle scale 5.5%Humanity’s Last ExamPotential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. [variant] Published May 23, 2025 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		5.5 reasoning
lmarena text 1339.1 eloLMArena / ArenaPublished source fact [variant] text / overallPublished Oct 2, 2026 Retrieved Oct 8, 2026 · CC-BY-4.0
Open source ↗ 		66.7 preference
math level 5 84.4%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 22, 2025 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		84.4 math
otis mock aime 2024 2025 28.9%Epoch AI BenchmarkingEpoch-owned evaluation mean score; scores only, no benchmark questions [variant] Published May 22, 2025 Retrieved Oct 8, 2026 · CC-BY
Open source ↗ 		28.9 math
swe bench pro public 9.1%SWE-bench Pro (public)Published steward score [variant] Published Sep 19, 2025 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		9.1 coding
swe bench verified 57%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Artemis Agent v2Published Sep 24, 2025 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		57.0 coding
swe bench verified 74.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Harness AIPublished Jul 31, 2025 Retrieved Oct 8, 2026 · factual citation
Open source ↗ 		74.8 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)

  • ARC Prize · arrived Oct 8, 2026
  • Epoch AI Benchmarking · arrived Oct 8, 2026
  • Humanity’s Last Exam · arrived Oct 8, 2026
  • LMArena / Arena · arrived Oct 8, 2026

pending Awaiting (3)

  • Official model cards via models.dev · carries 4% of expected weight
  • LiveBench · 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.