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
Explore Claude Haiku 5.5 Benchmark scores, token price tiers and context caps — each figure cited to its source, with no hands-on testing.
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
Claude Haiku 5.5 Benchmark Data, Explained Simply
Launch-time scores, token price tiers and per-effort costs are shown alongside the setup behind each run and the day it was retrieved.
- Scores That Cannot Be AveragedElo, partial-credit, coding and accuracy metrics sit on incompatible scales, so blending them into one figure is misleading.
- Built for High-Volume Repetitive WorkAimed at extraction, classification and summarisation jobs that run thousands of times over.
- Two Footnotes That Rewrite the TablesDiscounted rates stop at 100K tokens, and the 72.4% computer-use figure is partial credit rather than a pass rate.
Putting Haiku 5.5 Benchmark Data to Work
Three steps for converting published Haiku 5.5 Benchmark figures into a practical workload choice.
Key Claude Haiku 5.5 Benchmark Findings
Declared specs, cost tiers, coding outcomes, computer-use results and third-party index readings for Claude Haiku 5.5.
Context Window and Output Ceiling
Inputs are text plus images and output is text, with adaptive thinking on. One million tokens of context and a 128,000-token output cap dwarf Haiku 4.5's 200,000 and 64,000.
Pricing Split by Prompt Length
Pass 100,000 prompt tokens and input, output and caching each move to a tier five times the cheap one. OpenAI's base Standard band stretches to 272,000 input tokens.
Terminal-Bench 4.0: Finished Task Runs
Haiku's 39.2% launch score clears Luna by a wide margin but sits under the published Sol rows. Runs allow an eight-hour agent timeout, and the 2.1 or 3.0 figures belong to an earlier experiment.
FrontierCode Grading and Cost per Effort
Grading weighs correctness, tests, scope, style and repo conventions. Haiku lands at 46.4% on max effort and 41.6% at medium for $0.13 a rollout, while stepping from xhigh to max doubles spend for half a point.
OSWorld 2.1: Partial Credit vs Strict Pass
Eighty-two offline tasks, five attempts apiece, 1080p screenshots and a 500-step ceiling define the run. For a workflow that has to finish, 37.1% is the strict rate worth trusting.
Third-Party Index Scores and Tool Gains
Artificial Analysis lists Haiku across all five efforts on Intelligence Index v4.3.2 with rounded task costs. HLE reads 45.9% without tools and 57.4% with them — a lift from the surrounding system.
Claude Haiku 5.5 Benchmark: Common Questions
Answers on Claude Haiku 5.5 Benchmark results, token pricing and hard limits.
How does Haiku 5.5 stack up against GPT-6 Luna and Sol?
Across knowledge work, screenshot tasks and narrow coding, Haiku trades blows with Luna. Sol and Sol 6.1 charge more and earn it on coding, while Sonnet 5.5 still tops most rows.
Why isn't the 72.4% computer-use figure a success rate?
Require every checkpoint to be met and the same run drops to 37.1%. An agent can locate and edit the right file, then save it in the wrong format or quit before the last action. Add an end-state check.
At what point does Haiku 5.5 move to the pricier tier?
Only prompts of up to 100,000 tokens get the lowest rates; beyond that every category costs five times as much. 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?
No parameter count, active-parameter figure, layer count or training compute appears in the published specs. 'Small' describes a product tier, not an architecture, so local GPU estimates have nothing to stand on.
Does more reasoning effort always produce better output?
Not always. Sol 6.1 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. Extra effort adds tokens, latency and more chances to drift off task.
Why do identical models post different figures in different tables?
Sonnet reads 70.6% in Anthropic's launch table and 61.8% on the public leaderboard snapshot, where Haiku shows no row at all. Artificial Analysis removed its 'Default Fallback' tag, yet Anthropic's migration guide still states no server-side fallback exists.
Put Claude Haiku 5.5 Benchmark Scores to the Test
Choose one workload, fix the effort level, and see whether Haiku 5.5 clears the quality bar you actually need.