SI Index Data as of Oct 9, 2026

Claude Haiku 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
47.3
SI Score (method si-v3-retained-evidence-2)
33% confidence 33 percent, Low confidence — 3 of 8 expected sources in
Coverage 27% of expected source weight · 100% confidence at 80% coverage

Pillar breakdown

Coding (weight 40 percent) 55.4
Math (weight 15 percent) —
Preference (weight 15 percent) —
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
$1.00Anthropic 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
$5.00Anthropic 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
Oct 15, 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

22 results
Benchmark Raw result Normalized (0–100) Pillar
arc agi v1 public eval 26.6%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-haiku-4-5-20251001Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		26.6 reasoning
arc agi v1 public eval 51.4%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-haiku-4-5-20251001-thinking-16kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		51.4 reasoning
arc agi v1 public eval 27.1%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-haiku-4-5-20251001-thinking-1kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		27.1 reasoning
arc agi v1 public eval 62.9%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-haiku-4-5-20251001-thinking-32kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		62.9 reasoning
arc agi v1 public eval 45%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-haiku-4-5-20251001-thinking-8kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		45.0 reasoning
arc agi v1 semi private 14.3%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-haiku-4-5-20251001Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		14.3 reasoning
arc agi v1 semi private 37.3%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-haiku-4-5-20251001-thinking-16kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		37.3 reasoning
arc agi v1 semi private 16.8%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-haiku-4-5-20251001-thinking-1kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		16.8 reasoning
arc agi v1 semi private 47.7%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-haiku-4-5-20251001-thinking-32kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		47.7 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-haiku-4-5-20251001-thinking-8kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		25.5 reasoning
arc agi v2 public eval 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-haiku-4-5-20251001Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		0.0 reasoning
arc agi v2 public eval 4.2%ARC PrizeARC Prize steward-published result; exact edition/subset; publication time is HTTP Last-Modified of the aggregate export, not the evaluation date. [variant] claude-haiku-4-5-20251001-thinking-16kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		4.2 reasoning
arc agi v2 public eval 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-haiku-4-5-20251001-thinking-1kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		0.0 reasoning
arc agi v2 public eval 5.1%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-haiku-4-5-20251001-thinking-32kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		5.1 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-haiku-4-5-20251001-thinking-8kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		2.1 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] claude-haiku-4-5-20251001Published Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		1.3 reasoning
arc agi v2 semi private 2.8%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-haiku-4-5-20251001-thinking-16kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		2.8 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-haiku-4-5-20251001-thinking-1kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		1.3 reasoning
arc agi v2 semi private 4.0%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-haiku-4-5-20251001-thinking-32kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		4.0 reasoning
arc agi v2 semi private 1.7%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-haiku-4-5-20251001-thinking-8kPublished Oct 6, 2026 Retrieved Oct 9, 2026 · factual citation
Open source ↗ 		1.7 reasoning
swe bench pro public 39.5%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 ↗ 		39.5 coding
swe bench verified 66.6%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 ↗ 		66.6 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 (3)

  • ARC Prize · arrived Oct 8, 2026
  • Official model cards via models.dev · arrived Oct 8, 2026
  • SWE-bench Verified · arrived Oct 8, 2026

pending Awaiting (5)

  • Epoch AI Benchmarking · carries 23% of expected weight
  • Humanity’s Last Exam · carries 11% of expected weight
  • LiveBench · carries 11% of expected weight
  • LMArena / Arena · carries 23% 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.