ZMIME
Comparison · 2 models · Updated Oct 4, 2026

Claude Haiku 4.5 vs Claude Sonnet 4.5

Too close to call on our weighted score (Claude Haiku 4.5 58, Claude Sonnet 4.5 55). The right pick depends on what you value most.

  1. Anthropic

    Claude Haiku 4.5

    Released Oct 15, 2025

    58/100
    • ECI142.4
    • Price$1.00 / $5.00
    • Context200K
    Full specs Remove Claude Haiku 4.5

  2. Anthropic

    Claude Sonnet 4.5

    Released Sep 29, 2025

    55/100
    • ECI146.8
    • Price$3.00 / $15.00
    • Context200K
    Full specs Remove Claude Sonnet 4.5

  3. Add a model

    Make it a three-way comparison.

01 — Verdict

Too close to call

It is close. Our weighted score puts them within 3 points (Claude Haiku 4.5 58/100, Claude Sonnet 4.5 55/100), so choose by what matters most for your work: Claude Sonnet 4.5 for raw capability and Claude Haiku 4.5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityClaude Sonnet 4.5Capabilities Index (ECI): Claude Sonnet 4.5 146.8 · Claude Haiku 4.5 142.4
  • Lowest priceClaude Haiku 4.5Claude Haiku 4.5 $2.00 · Claude Sonnet 4.5 $6.00 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameClaude Haiku 4.5 200,000 · Claude Sonnet 4.5 200,000 tokens
  • Widest inputsSame inputsClaude Haiku 4.5: Text, Images, PDFs · Claude Sonnet 4.5: Text, Images, PDFs
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightClaude Haiku 4.5Claude Sonnet 4.5
CapabilityCapabilities Index (ECI)50%6974
Price25%3613
Inputs & features15%8080
Context window10%3232
Overall100%58/10055/100
02 — Side by side

Every spec in one table

Highlighted cells lead their row. Dashes mean the data is not published.

Claude Haiku 4.5 vs Claude Sonnet 4.5 specifications side by side
SpecificationClaude Haiku 4.5AnthropicClaude Sonnet 4.5Anthropic
Capability
Capabilities Index (ECI)142.4146.8 (best)
ECI rank#90 of 148#64 of 148 (best)
GPQA DiamondGraduate-level science questions71.2%82.3% (best)
FrontierMath Tiers 1–3Research-level mathematics—23.9%
OTIS Mock AIME 2024–2025Competition mathematics66.7%77.8% (best)
SWE-bench VerifiedFixing real GitHub issues—71.3%
SimpleQA VerifiedShort factual questions13.2%30.7% (best)
Price per million tokens
Input$1.00 (best)$3.00
Output$5.00 (best)$15.00
Cached input$0.10 (best)$0.30
Blended (3:1)$2.00 (best)$6.00
Long-context rateSame rateSame rate
Price sourceOfficial Anthropic APIOfficial Anthropic API
Limits
Context window200,000 tokens200,000 tokens
Max output64,000 tokens64,000 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsYesYes
AudioNoNo
VideoNoNo
ReasoningYesYes
Tool callingYesYes
Structured outputYesYes
Availability
WeightsProprietaryProprietary
API model IDclaude-haiku-4-5claude-sonnet-4-5
API providers34 (best)28
ReleasedOct 15, 2025Sep 29, 2025
Knowledge cutoffFeb 28, 2025Jul 31, 2025
03 — Cost

What would a month cost?

Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.

  • Claude Haiku 4.5$20.00
  • Claude Sonnet 4.5$60.00
04 — Questions

Which should you choose?

Which is better: Claude Haiku 4.5 or Claude Sonnet 4.5?

It is close. Our weighted score puts them within 3 points (Claude Haiku 4.5 58/100, Claude Sonnet 4.5 55/100), so choose by what matters most for your work: Claude Sonnet 4.5 for raw capability and Claude Haiku 4.5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Haiku 4.5 or Claude Sonnet 4.5?

Claude Haiku 4.5 is cheaper at $1.00 input / $5.00 output per million tokens (official Anthropic API price). Claude Sonnet 4.5 costs $3.00 input / $15.00 output per million tokens (official Anthropic API price). At a typical mix of three input tokens to one output token, that is $2.00 per million tokens for Claude Haiku 4.5 versus $6.00 for Claude Sonnet 4.5 (3× as much).

Which scores higher on benchmarks?

Claude Sonnet 4.5 scores higher on the Capabilities Index (ECI): Claude Sonnet 4.5 146.8 (#64 of 148) and Claude Haiku 4.5 142.4 (#90 of 148). Their confidence ranges do not overlap (145.3–148.5 vs 139.5–144.3), so the gap is a real one. On individual benchmarks: GPQA Diamond — Claude Sonnet 4.5 82.3%, Claude Haiku 4.5 71.2%; OTIS Mock AIME 2024–2025 — Claude Sonnet 4.5 77.8%, Claude Haiku 4.5 66.7%; SimpleQA Verified — Claude Sonnet 4.5 30.7%, Claude Haiku 4.5 13.2%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 4.5 yet, so there is no like-for-like coding score. On overall capability, Claude Sonnet 4.5 leads, which tends to carry over to coding, but test on your own codebase. Both support tool calling for agent workflows.

Which has the bigger context window?

Claude Haiku 4.5 and Claude Sonnet 4.5 share the same 200,000-token context window. Maximum output per response: Claude Haiku 4.5 up to 64,000, Claude Sonnet 4.5 up to 64,000 tokens.

Which can read images, PDFs, audio or video?

Claude Haiku 4.5 accepts text, images and PDFs; Claude Sonnet 4.5 accepts text, images and PDFs. They handle the same number of input types.

Are any of these open source?

No. Claude Haiku 4.5 and Claude Sonnet 4.5 are proprietary and only available through APIs and apps.

Which is newer?

Claude Haiku 4.5 is the newest, released Oct 15, 2025. Claude Sonnet 4.5 came out Sep 29, 2025. Knowledge cutoff: Claude Haiku 4.5 Feb 28, 2025, Claude Sonnet 4.5 Jul 31, 2025.

How do you decide the winner?

Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.

05 — Keep comparing

Related comparisons