Haiku 5.5 Benchmark Model Profile
A single entry in Kingy AI's source-referenced model catalog — Claude Haiku 5.5 benchmark results alongside provider, family, modality and API access details.
None

None

None

Long Story Video Skill

Turn your idea into 10s–10min video—AI writes scripts, prompts, and generates footage automatically.

Ads Video Skill

Ads Video Skill

Generate professional ads and sales videos—AI auto-generates scripts, prompts, and footage.

3D Science Explainer Video Skill

Convert scientific concepts into stunning 3D explain animations

AI Video Prompt Generator

Feedback

freeTrialImage.bannerPity

freeTrialImage.upgradeUnlock

  • ✓freeTrialImage.benefitHd
  • ✓freeTrialImage.benefitWatermark
  • ✓freeTrialImage.benefitUnlimited

Haiku 5.5 Benchmark

See what the Haiku 5.5 Benchmark reports — launch task scores, token price bands and context caps, with every number traced back to its source.

All Tools

Discover our comprehensive AI-powered animation toolkit

What These Haiku 5.5 Benchmark Numbers Mean for Your Stack

Launch-day scores, token price tiers and per-effort spend, documented alongside the settings and dates they were collected.

  • How Each Launch Metric Is Scored
    Elo ratings, partial credit, coding passes and accuracy percentages sit on separate scales, so averaging them distorts the picture.
  • Built for High-Volume Repetition
    Suited to extraction, classification and summarization jobs that run thousands of times a day.
  • Two Footnotes That Reshape the Tables
    Low rates end past 100K prompt tokens, and the 72.4% computer-use figure counts partial credit rather than full task passes.

A Three-Step Way to Interpret the Haiku 5.5 Benchmark

Follow three steps to convert published Haiku 5.5 benchmark figures into a practical workload decision.

What the Haiku 5.5 Benchmark Data Shows

Specifications, price tiers, coding outcomes, computer-use results and third-party index data for Claude Haiku 5.5, all taken from published material.

Context Window and Output Ceiling

Text and image input, text output, adaptive thinking enabled. A one-million-token context and a 128,000-token output cap far exceed Haiku 4.5's 200,000 and 64,000.

Pricing Split by Prompt Length

Pass 100,000 prompt tokens and input, output and caching all move to a tier priced five times higher, while OpenAI's standard band reaches 272,000 input tokens.

Terminal-Bench 4.0 Task Completion

The 39.2% launch score clears Luna by a wide margin yet trails the published Sol entries; runs allow an eight-hour agent timeout, and 2.1 or 3.0 results come from an earlier experiment.

FrontierCode Mergeability vs. Effort Spend

Scoring weighs correctness, tests, scope, style and repo conventions. Haiku reaches 46.4% at max effort and 41.6% at medium for $0.13 per rollout; stepping from xhigh to max doubles cost for half a point.

OSWorld 2.1: Partial Credit vs. Strict Pass

The setup: 82 offline tasks, five attempts each, 1080p screenshots and a 500-step limit. When a workflow has to finish end to end, 37.1% is the figure to trust.

Third-Party Index Scores and Tool Gains

Artificial Analysis lists Haiku at all five effort levels on Intelligence Index v4.3.2 with rounded task costs; HLE moves from 45.9% without tools to 57.4% with them, a lift that comes from the surrounding harness.

FAQ

Questions About the Haiku 5.5 Benchmark

Straight answers on Claude Haiku 5.5 benchmark results, token pricing and context limits.

1

Where does Haiku 5.5 stand next to GPT-6 Luna and GPT-6 Sol?

Across knowledge work, screenshot handling and tight coding jobs, Haiku matches Luna blow for blow. Sol and Sol 6.1 charge more and justify it on coding, yet Sonnet 5.5 still tops most rows.

2

Why doesn't the 72.4% computer-use figure count as a success rate?

Require every checkpoint and the same run drops to 37.1%. An agent may find and edit the correct file, then save it in the wrong format or quit before the final action — so add an end-state check.

3

At what point does Haiku 5.5 move to the higher price tier?

Prompts up to 100,000 tokens qualify for the lowest rates; beyond that, every category costs five times as much. Anthropic's 90%, 50% and roughly 75% savings claims rest on different baselines.

4

Could Haiku 5.5 run locally, and what GPU memory would it take?

The published specs list no parameter count, active-parameter number, layer count or training compute. 'Small' describes a product tier rather than an architecture, so any local GPU estimate rests on nothing.

5

Does raising reasoning effort always produce better output?

No. Sol 6.1 actually scores higher at medium than at max, and Haiku's 0.2-point lead over Sonnet at max is too thin to call a win; extra effort adds tokens, latency and room to drift off task.

6

Why does one model show different numbers across tables?

Sonnet appears at 70.6% in Anthropic's launch table and 61.8% on the public leaderboard snapshot, where Haiku had no visible row. Artificial Analysis removed its 'Default Fallback' tag, while Anthropic's migration guide still states no server-side fallback exists.

Put the Haiku 5.5 Benchmark Up Against Your Own Workload

Choose a single workload, fix the effort setting, and measure Haiku 5.5 against the quality bar you already accept.