ZMIME
Comparison · 2 models · Updated Nov 2, 2026

Claude Sonnet 3.5 v2 vs Claude Haiku 3.5

Too close to call on our weighted score (Claude Haiku 3.5 46, Claude Sonnet 3.5 v2 44). The right pick depends on what you value most.

  1. Anthropic

    Claude Sonnet 3.5 v2

    Released Oct 22, 2024

    44/100
    • ECI133.4
    • Price$2.80 / $14.00
    • Context200K
    Full specs Remove Claude Sonnet 3.5 v2

  2. Anthropic

    Claude Haiku 3.5

    Released Oct 22, 2024

    46/100
    • ECI127.0
    • Price$0.80 / $4.00
    • Context200K
    Full specs Remove Claude Haiku 3.5

  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 2 points (Claude Haiku 3.5 46/100, Claude Sonnet 3.5 v2 44/100), so choose by what matters most for your work: Claude Sonnet 3.5 v2 for raw capability and Claude Haiku 3.5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityClaude Sonnet 3.5 v2Capabilities Index (ECI): Claude Sonnet 3.5 v2 133.4 · Claude Haiku 3.5 127.0
  • Lowest priceClaude Haiku 3.5Claude Haiku 3.5 $1.60 · Claude Sonnet 3.5 v2 $5.60 per 1M tokens (3:1 blend)
  • Longest contextAbout the sameClaude Sonnet 3.5 v2 200,000 · Claude Haiku 3.5 200,000 tokens
  • Widest inputsSame inputsClaude Sonnet 3.5 v2: Text, Images, PDFs · Claude Haiku 3.5: Text, Images, PDFs
  • Self-hostingNo open weightsBoth are available only through APIs
How the score is built
MeasureWeightClaude Sonnet 3.5 v2Claude Haiku 3.5
CapabilityCapabilities Index (ECI)50%5648
Price25%1438
Inputs & features15%6060
Context window10%3232
Overall100%44/10046/100
02 — Side by side

Every spec in one table

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

Claude Sonnet 3.5 v2 vs Claude Haiku 3.5 specifications side by side
SpecificationClaude Sonnet 3.5 v2AnthropicClaude Haiku 3.5Anthropic
Capability
Capabilities Index (ECI)133.4 (best)127.0
ECI rank#133 of 165 (best)#147 of 165
GPQA DiamondGraduate-level science questions55.3% (best)38.1%
OTIS Mock AIME 2024–2025Competition mathematics8.5% (best)4.3%
Price per million tokens
Input$2.80$0.80 (best)
Output$14.00$4.00 (best)
Cached input——
Blended (3:1)$5.60$1.60 (best)
Long-context rateSame rateSame rate
Price sourceMedian of 2 providersMedian of 3 providers
Limits
Context window200,000 tokens200,000 tokens
Max output8,192 tokens8,192 tokens
Inputs and features
TextYesYes
ImagesYesYes
PDFsYesYes
AudioNoNo
VideoNoNo
ReasoningNoNo
Tool callingYesYes
Structured outputNoNo
Availability
WeightsProprietaryProprietary
API model ID——
API providers34 (best)
ReleasedOct 22, 2024Oct 22, 2024
Knowledge cutoffApr 30, 2024Jul 31, 2024
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 Sonnet 3.5 v2$56.00
  • Claude Haiku 3.5$16.00
04 — Questions

Which should you choose?

Which is better: Claude Sonnet 3.5 v2 or Claude Haiku 3.5?

It is close. Our weighted score puts them within 2 points (Claude Haiku 3.5 46/100, Claude Sonnet 3.5 v2 44/100), so choose by what matters most for your work: Claude Sonnet 3.5 v2 for raw capability and Claude Haiku 3.5 on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Sonnet 3.5 v2 or Claude Haiku 3.5?

Claude Haiku 3.5 is cheaper at $0.80 input / $4.00 output per million tokens (median across 3 API providers). Claude Sonnet 3.5 v2 costs $2.80 input / $14.00 output per million tokens (median across 2 API providers). At a typical mix of three input tokens to one output token, that is $1.60 per million tokens for Claude Haiku 3.5 versus $5.60 for Claude Sonnet 3.5 v2 (3.5× as much).

Which scores higher on benchmarks?

Claude Sonnet 3.5 v2 scores higher on the Capabilities Index (ECI): Claude Sonnet 3.5 v2 133.4 (#133 of 165) and Claude Haiku 3.5 127.0 (#147 of 165). The confidence ranges of the top two overlap (128.5–137.7 vs 121.4–129.2), so treat the gap as small. On individual benchmarks: GPQA Diamond — Claude Sonnet 3.5 v2 55.3%, Claude Haiku 3.5 38.1%; OTIS Mock AIME 2024–2025 — Claude Sonnet 3.5 v2 8.5%, Claude Haiku 3.5 4.3%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Sonnet 3.5 v2 and Claude Haiku 3.5 yet, so there is no like-for-like coding score. On overall capability, Claude Sonnet 3.5 v2 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 Sonnet 3.5 v2 and Claude Haiku 3.5 share the same 200,000-token context window. Maximum output per response: Claude Sonnet 3.5 v2 up to 8,192, Claude Haiku 3.5 up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Claude Sonnet 3.5 v2 accepts text, images and PDFs; Claude Haiku 3.5 accepts text, images and PDFs. They handle the same number of input types.

Are any of these open source?

No. Claude Sonnet 3.5 v2 and Claude Haiku 3.5 are proprietary and only available through APIs and apps.

Which is newer?

Claude Sonnet 3.5 v2 is the newest, released Oct 22, 2024. Claude Haiku 3.5 came out Oct 22, 2024. Knowledge cutoff: Claude Sonnet 3.5 v2 Apr 30, 2024, Claude Haiku 3.5 Jul 31, 2024.

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 Nov 2, 2026.

05 — Keep comparing

Related comparisons