ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Claude Haiku 3 vs Qwen2.5-VL 72B Instruct vs Gemma 2 27B

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

Price in rating: Included · Exclude price

  1. Anthropic

    Claude Haiku 3

    Released Mar 13, 2024

    57/100
    • ECI117.8
    • Price$0.25 / $1.25
    • Context200K
  2. Alibaba (Qwen)

    Qwen2.5-VL 72B Instruct

    Released Jan 26, 2025

    45/100
    • ECI—
    • Price$1.01 / $1.01
    • Context131K
  3. Google

    Gemma 2 27B

    Released Jul 13, 2024

    28/100
    • ECI118.6
    • Price$0.65 / $0.65
    • Context8K
01 — Verdict

Capability evidence is incomplete

There is not enough shared capability evidence to name an overall winner. The scores (Claude Haiku 3 57/100, Qwen2.5-VL 72B Instruct 45/100, Gemma 2 27B 28/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. 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 · Gemma 2 27B $0.65 · Qwen2.5-VL 72B Instruct $1.01 per 1M tokens (3:1 blend)
  • Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Qwen2.5-VL 72B Instruct 131,072 · Gemma 2 27B 8,192 tokens
  • Widest inputsClaude Haiku 3Claude Haiku 3: Text, Images, PDFs · Qwen2.5-VL 72B Instruct: Text, Images · Gemma 2 27B: Text
  • Self-hostingQwen2.5-VL 72B Instruct and Gemma 2 27BPublishes downloadable weights
How the score is built
MeasureWeightClaude Haiku 3Qwen2.5-VL 72B InstructGemma 2 27B
Price50%614856
Inputs & features30%60500
Context window20%39320
Specs & price only100%57/10045/10028/100

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 Qwen2.5-VL 72B Instruct vs Gemma 2 27B specifications side by side
SpecificationClaude Haiku 3AnthropicQwen2.5-VL 72B InstructAlibaba (Qwen)Gemma 2 27BGoogle
Capability
Capabilities Index (ECI)117.8—118.6 (best)
ECI rank#154 of 158—#152 of 158 (best)
GPQA DiamondGraduate-level science questions36.3%—36.5% (best)
OTIS Mock AIME 2024–2025Competition mathematics1.8% (best)—1.4%
Price per million tokens
Input$0.25 (best)$1.01$0.65
Output$1.25$1.01$0.65 (best)
Cached input———
Blended (3:1)$0.50 (best)$1.01$0.65
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersMedian of 5 providersMedian of 3 providers
Limits
Context window200,000 tokens (best)131,072 tokens8,192 tokens
Max output4,096 tokens8,192 tokens (best)2,048 tokens
Inputs and features
TextYesYesYes
ImagesYesYesNo
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesYesNo
Structured outputNoNoNo
Availability
WeightsProprietaryOpenOpen
API model ID———
API providers35 (best)3
ReleasedMar 13, 2024Jan 26, 2025Jul 13, 2024
Knowledge cutoffAug 31, 2023Apr 2024Jun 30, 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
  • Qwen2.5-VL 72B Instruct$12.12
  • Gemma 2 27B$7.80
04 — Questions

Which should you choose?

Which is better: Claude Haiku 3, Qwen2.5-VL 72B Instruct or Gemma 2 27B?

There is not enough shared capability evidence to name an overall winner. The scores (Claude Haiku 3 57/100, Qwen2.5-VL 72B Instruct 45/100, Gemma 2 27B 28/100) compare the available specifications and price. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.

Which is cheaper, Claude Haiku 3, Qwen2.5-VL 72B Instruct or Gemma 2 27B?

Claude Haiku 3 is cheaper at $0.25 input / $1.25 output per million tokens (median across 3 API providers). Gemma 2 27B costs $0.65 input / $0.65 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). At a typical mix of three input tokens to one output token, that is $0.50 per million tokens for Claude Haiku 3 versus $0.65 for Gemma 2 27B (1.3× as much) and $1.01 for Qwen2.5-VL 72B Instruct (2× 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, Qwen2.5-VL 72B Instruct has not been scored yet and Gemma 2 27B has an ECI of 118.6.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 3, Qwen2.5-VL 72B Instruct and Gemma 2 27B yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that Gemma 2 27B does not support tool calling, which most coding agents need.

Which has the bigger context window?

Claude Haiku 3 has the largest context window at 200,000 tokens, against 131,072 for Qwen2.5-VL 72B Instruct and 8,192 for Gemma 2 27B. Maximum output per response: Claude Haiku 3 up to 4,096, Qwen2.5-VL 72B Instruct up to 8,192, Gemma 2 27B up to 2,048 tokens.

Which can read images, PDFs, audio or video?

Claude Haiku 3 accepts text, images and PDFs; Qwen2.5-VL 72B Instruct accepts text and images; Gemma 2 27B accepts text. Claude Haiku 3 handles the widest range of inputs.

Are any of these open source?

Qwen2.5-VL 72B Instruct and Gemma 2 27B publishes its weights and can be self-hosted; Claude Haiku 3 is proprietary.

Which is newer?

Qwen2.5-VL 72B Instruct is the newest, released Jan 26, 2025. Gemma 2 27B came out Jul 13, 2024; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Claude Haiku 3 Aug 31, 2023, Qwen2.5-VL 72B Instruct Apr 2024, Gemma 2 27B Jun 30, 2024.

How do you decide the winner?

This rating uses price (50%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (30%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (20%, 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.