SI Index Data as of Oct 9, 2026

Claude Sonnet 4.5 (latest): Price, Context, Benchmarks, and Release Details

Anthropic provisional listing · first seen Oct 8, 2026 · score computed Oct 9, 2026, 01:50 UTC
48.2
SI Score (method si-v3-retained-evidence-2)
43% confidence 43 percent, Low confidence — 4 of 9 expected sources in
Coverage 34% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 57.9
Math (weight 15 percent) —
Preference (weight 15 percent) —
Reasoning (weight 30 percent) 27.3

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
$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
200Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Max output
64Kmodels.devPublished source fact Retrieved Oct 9, 2026 · MIT
Open source ↗
Released
Sep 29, 2025models.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

25 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 35.4%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-4-5-20250929Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		35.4 reasoning
arc agi v1 public eval 63.6%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-4-5-20250929-thinking-16kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		63.6 reasoning
arc agi v1 public eval 36.6%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-4-5-20250929-thinking-1kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		36.6 reasoning
arc agi v1 public eval 73.8%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-4-5-20250929-thinking-32kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		73.8 reasoning
arc agi v1 public eval 53.5%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-4-5-20250929-thinking-8kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		53.5 reasoning
arc agi v1 semi private 25.5%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-4-5-20250929Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		25.5 reasoning
arc agi v1 semi private 48.3%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-4-5-20250929-thinking-16kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		48.3 reasoning
arc agi v1 semi private 31%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-4-5-20250929-thinking-1kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		31.0 reasoning
arc agi v1 semi private 63.7%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-4-5-20250929-thinking-32kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		63.7 reasoning
arc agi v1 semi private 46.5%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-4-5-20250929-thinking-8kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		46.5 reasoning
arc agi v2 public eval 3.8%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-4-5-20250929Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		3.8 reasoning
arc agi v2 public eval 6.5%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-4-5-20250929-thinking-16kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		6.5 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-4-5-20250929-thinking-1kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		2.1 reasoning
arc agi v2 public eval 14.7%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-4-5-20250929-thinking-32kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		14.7 reasoning
arc agi v2 public eval 4.9%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-4-5-20250929-thinking-8kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		4.9 reasoning
arc agi v2 semi private 3.8%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-4-5-20250929Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		3.8 reasoning
arc agi v2 semi private 6.9%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-4-5-20250929-thinking-16kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		6.9 reasoning
arc agi v2 semi private 5.8%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-4-5-20250929-thinking-1kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		5.8 reasoning
arc agi v2 semi private 13.6%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-4-5-20250929-thinking-32kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		13.6 reasoning
arc agi v2 semi private 6.9%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-4-5-20250929-thinking-8kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		6.9 reasoning
swe bench pro public 43.6%Official model cards via models.devLab-reported; metric resolve rate; transcribed by MIT models.dev catalog; not independently evaluated [variant] public Retrieved Oct 9, 2026 · factual citation; MIT transcription
Open source ↗ 		43.6 coding
swe bench pro public 43.6%SWE-bench Pro (public)Published steward score [variant] Published Sep 19, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		43.6 coding
swe bench verified 70.6%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; 1.13.3Published Sep 29, 2025 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		70.6 coding
swe bench verified 71.4%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] mini-SWE-agent; high; 2.0.0Published Feb 17, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		71.4 coding
swe bench verified 74.8%SWE-bench VerifiedSWE-bench published model plus agent result; harness retained, not a base model evaluation [variant] Sonar Foundation AgentPublished Nov 3, 2025 Retrieved Oct 9, 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
  • Official model cards via models.dev · arrived Oct 8, 2026
  • SWE-bench Verified · arrived Oct 8, 2026
  • SWE-bench Pro (public) · arrived Oct 8, 2026

pending Awaiting (5)

  • Epoch AI Benchmarking · carries 20% of expected weight
  • Humanity’s Last Exam · carries 10% of expected weight
  • LiveBench · carries 10% of expected weight
  • LMArena / Arena · carries 20% of expected weight
  • Terminal-Bench · carries 5% 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.