ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Haiku 3 vs Nova Pro vs Qwen2.5-VL 72B Instruct

No independent capability benchmark covers every model here yet. The score uses inputs & features and context window.

Price in rating: Excluded · Include price

  1. Anthropic

    Claude Haiku 3

    Released Mar 13, 2024

    52/100
    • ECI117.8
    • Price$0.25 / $1.25
    • Context200K
  2. Amazon

    Nova Pro

    Released Dec 3, 2024

    60/100
    • ECI—
    • Price$0.80 / $3.20
    • Context300K
  3. Alibaba (Qwen)

    Qwen2.5-VL 72B Instruct

    Released Jan 26, 2025

    43/100
    • ECI—
    • Price$1.01 / $1.01
    • Context131K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Nova Pro 60/100, Claude Haiku 3 52/100, Qwen2.5-VL 72B Instruct 43/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

  • CapabilityNot enough dataNo independent benchmark covers every model here yet
  • Lowest priceClaude Haiku 3Claude Haiku 3 $0.50 · Qwen2.5-VL 72B Instruct $1.01 · Nova Pro $1.40 per 1M tokens (3:1 blend)
  • Longest contextNova ProNova Pro 300,000 · Claude Haiku 3 200,000 · Qwen2.5-VL 72B Instruct 131,072 tokens
  • Widest inputsNova ProClaude Haiku 3: Text, Images, PDFs · Nova Pro: Text, Images, PDFs, Video · Qwen2.5-VL 72B Instruct: Text, Images
  • Self-hostingQwen2.5-VL 72B InstructPublishes downloadable weights
How the score is built
MeasureWeightClaude Haiku 3Nova ProQwen2.5-VL 72B Instruct
Inputs & features60%607050
Context window40%394532
Specs only100%52/10060/10043/100

Left out because at least one model lacks the data: capability. The remaining weights were rescaled.

02 — Side by side

Every spec in one table

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

Claude Haiku 3 vs Nova Pro vs Qwen2.5-VL 72B Instruct specifications side by side
SpecificationClaude Haiku 3AnthropicNova ProAmazonQwen2.5-VL 72B InstructAlibaba (Qwen)
Capability
Capabilities Index (ECI)117.8——
ECI rank#154 of 158——
GPQA DiamondGraduate-level science questions36.3%——
OTIS Mock AIME 2024–2025Competition mathematics1.8%——
Price per million tokens
Input$0.25 (best)$0.80$1.01
Output$1.25$3.20$1.01 (best)
Cached input—$0.20—
Blended (3:1)$0.50 (best)$1.40$1.01
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersOfficial Amazon Bedrock APIMedian of 5 providers
Limits
Context window200,000 tokens300,000 tokens (best)131,072 tokens
Max output4,096 tokens10,000 tokens (best)8,192 tokens
Inputs and features
TextYesYesYes
ImagesYesYesYes
PDFsYesYesNo
AudioNoNoNo
VideoNoYesNo
ReasoningNoNoNo
Tool callingYesYesYes
Structured outputNoNoNo
Availability
WeightsProprietaryProprietaryOpen
API model ID—amazon.nova-pro-v1:0—
API providers39 (best)5
ReleasedMar 13, 2024Dec 3, 2024Jan 26, 2025
Knowledge cutoffAug 31, 2023Oct 2024Apr 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 Haiku 3$5.00
  • Nova Pro$14.40
  • Qwen2.5-VL 72B Instruct$12.12
04 — Questions

Which should you choose?

Which is better: Claude Haiku 3, Nova Pro or Qwen2.5-VL 72B Instruct?

There is not enough shared capability evidence to name an overall winner. The scores (Nova Pro 60/100, Claude Haiku 3 52/100, Qwen2.5-VL 72B Instruct 43/100) compare the available specifications only. The score weighs inputs & features 60%, context window 40%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Claude Haiku 3, Nova Pro or Qwen2.5-VL 72B Instruct?

Claude Haiku 3 is cheaper at $0.25 input / $1.25 output per million tokens (median across 3 API providers). Qwen2.5-VL 72B Instruct costs $1.01 input / $1.01 output per million tokens (median across 5 API providers); Nova Pro costs $0.80 input / $3.20 output per million tokens (official Amazon Bedrock API price). At a typical mix of three input tokens to one output token, that is $0.50 per million tokens for Claude Haiku 3 versus $1.01 for Qwen2.5-VL 72B Instruct (2× as much) and $1.40 for Nova Pro (2.8× as much).

Which scores higher on benchmarks?

There is no independent benchmark that covers all three models yet. Claude Haiku 3 has an ECI of 117.8, Nova Pro has not been scored yet and Qwen2.5-VL 72B Instruct has not been scored yet.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 3, Nova Pro and Qwen2.5-VL 72B Instruct yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.

Which has the bigger context window?

Nova Pro has the largest context window at 300,000 tokens, against 200,000 for Claude Haiku 3 and 131,072 for Qwen2.5-VL 72B Instruct. Maximum output per response: Claude Haiku 3 up to 4,096, Nova Pro up to 10,000, Qwen2.5-VL 72B Instruct up to 8,192 tokens.

Which can read images, PDFs, audio or video?

Claude Haiku 3 accepts text, images and PDFs; Nova Pro accepts text, images, PDFs and video; Qwen2.5-VL 72B Instruct accepts text and images. Nova Pro handles the widest range of inputs.

Are any of these open source?

Qwen2.5-VL 72B Instruct publishes its weights and can be self-hosted; Claude Haiku 3 and Nova Pro is proprietary.

Which is newer?

Qwen2.5-VL 72B Instruct is the newest, released Jan 26, 2025. Nova Pro came out Dec 3, 2024; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Claude Haiku 3 Aug 31, 2023, Nova Pro Oct 2024, Qwen2.5-VL 72B Instruct Apr 2024.

How do you decide the winner?

This rating uses inputs & features (60%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (40%, 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 18, 2026.