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
Claude Haiku 5.5 benchmark results gathered from published evaluations: task scores, token pricing tiers and hard limits, each tied 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.
Veo3.1
Create Stunning Videos with Veo3.1
FLUX 3 Video Generator
Kling 3.0
Next-Gen AI Video Generator
Grok Video Generator
Create Videos from Text or Images with AI
MiniMax H3 video generator
MiniMax H3 AI Video Generator
Put the Haiku 5.5 Benchmark Numbers to Work
Launch-day figures, price tiers and per-effort spend, each stored next to the settings and capture date behind it.
- What Each Launch Figure Really TracksElo, partial-credit, coding and accuracy scores sit on different scales, so averaging them makes no sense.
- Cost Efficiency for High-Volume TasksDesigned for extraction, classification and summarisation runs that repeat thousands of times.
- Two Footnotes That Reshape the TablesDiscounted pricing ends at 100K tokens, and the 72.4% computer-use figure is partial credit rather than a pass rate.
Turning Haiku 5.5 Benchmark Data Into a Decision
Three moves that convert published Claude Haiku 5.5 figures into a practical workload choice.
Claude Haiku 5.5 Benchmark: What the Data Shows
Specifications, pricing tiers, coding outcomes, computer-use results and third-party index figures, all drawn from published material on Claude Haiku 5.5.
Context Window and Output Ceiling
Text and images go in, text comes out, with adaptive thinking enabled. A million-token context and a 128,000-token output limit leave Haiku 4.5's 200,000 and 64,000 far behind.
Pricing Split by Prompt Length
Past 100,000 prompt tokens, input, output and caching all move into a tier priced five times higher. OpenAI's base Standard tier, by contrast, reaches 272,000 input tokens.
Terminal-Bench 4.0 Task Completion
The 39.2% launch result sits clearly above Luna but below the published Sol rows. Each task run allows an eight-hour agent timeout, and any 2.1 or 3.0 figures come from an earlier experiment.
FrontierCode Merges and Effort Spend
Scoring weighs correctness, tests, scope, style and repository conventions. At max effort Haiku reaches 46.4%, at medium 41.6% for $0.13 per rollout, while climbing from xhigh to max doubles cost for half a point.
OSWorld 2.1: Partial Credit vs. Strict Pass
The run covers 82 offline tasks with five tries each, 1080p screenshots and a 500-step cap. Where a workflow has to complete, 37.1% is the strict figure worth trusting.
Third-Party Index Scores and Tool Gains
Artificial Analysis lists Haiku across all five effort settings on Intelligence Index v4.3.2 with rounded task costs. HLE shows 45.9% unaided and 57.4% with tools — uplift that comes from the surrounding system.
Haiku 5.5 Benchmark Questions, Answered
Answers to frequent questions on Claude Haiku 5.5 evaluation figures, token pricing and hard limits.
How does Haiku 5.5 stack up against GPT-6 Luna and GPT-6 Sol?
Across knowledge tasks, screenshot work and small coding jobs, Haiku and Luna trade wins. 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 equal a success rate?
Once every checkpoint has to be satisfied, 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. Always add an end-state check.
At what point does Haiku 5.5 move into the higher price band?
The lowest rates apply only to prompts of up to 100,000 tokens; beyond that, every category is five times as expensive. Anthropic's 90%, 50% and ~75% savings claims each measure against a different baseline.
Could Haiku 5.5 run on local hardware, and how much VRAM would that take?
The published specifications list no parameter count, active parameters, layer total or training compute. 'Small' describes a product tier rather than an architecture, so VRAM estimates have nothing to stand on.
Does a higher reasoning effort setting always pay off?
Not reliably. Sol 6.1 actually scores higher at medium than at max, and Haiku's 0.2-point lead over Sonnet at max is too slim to call a win. More effort also means more tokens, more latency and more chances to drift off task.
Why do identical models post different numbers across tables?
Sonnet appears at 70.6% in Anthropic's launch table and 61.8% in the public leaderboard snapshot, where Haiku had no visible row. Artificial Analysis removed its 'Default Fallback' label, while Anthropic's migration guide still states that no server-side fallback exists.
Put the Haiku 5.5 Benchmark Up Against Your Own Workload
Choose a single workload, fix the effort level, and see whether Claude Haiku 5.5 clears your quality bar.