
None
None
Long Story Video Skill
Turn your idea into 10s–10min video—AI writes scripts, prompts, and generates footage automatically.

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
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
MiniMax H3
MiniMax H3 AI Video Generator
Seedance 2.5
The Future of AI Video Is Here.

Seedance 2.0
The Future of AI Video Is Here.

Seedance 2.0
The Future of AI Video Is Here.

AI Multi-Scene Shorts Generator
Create viral AI Shorts instantly

3D Science Video
Create 3D science videos easily

Suno AI Music Generator
Create Professional Music with AI

Free GPT Image 2.5
Next-generation image creator
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 ScoredElo ratings, partial credit, coding passes and accuracy percentages sit on separate scales, so averaging them distorts the picture.
- Built for High-Volume RepetitionSuited to extraction, classification and summarization jobs that run thousands of times a day.
- Two Footnotes That Reshape the TablesLow 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.
Questions About the Haiku 5.5 Benchmark
Straight answers on Claude Haiku 5.5 benchmark results, token pricing and context limits.
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.
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.
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.
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.
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.
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.
