ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemma 2 27B vs DeepSeek R1 0528 vs Claude Haiku 3

DeepSeek R1 0528 comes out ahead, 55 to 52 and 38 on our weighted score, though Claude Haiku 3 is 46% cheaper per token.

Price in rating: Included · Exclude price

  1. Google

    Gemma 2 27B

    Released Jul 13, 2024

    38/100
    • ECI118.6
    • Price$0.65 / $0.65
    • Context8K
  2. Our pick

    DeepSeek

    DeepSeek R1 0528

    Released May 28, 2025

    55/100
    • ECI140.8
    • Price$0.512 / $2.19
    • Context164K
  3. Anthropic

    Claude Haiku 3

    Released Mar 13, 2024

    52/100
    • ECI117.8
    • Price$0.25 / $1.25
    • Context200K
01 — Verdict

DeepSeek R1 0528 is our pick

DeepSeek R1 0528 is the better all-round choice, scoring 55/100 against Claude Haiku 3 (52) and Gemma 2 27B (38). It leads on capability. Claude Haiku 3 wins on price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityDeepSeek R1 0528Capabilities Index (ECI): DeepSeek R1 0528 140.8 · Gemma 2 27B 118.6 · Claude Haiku 3 117.8
  • Lowest priceClaude Haiku 3Claude Haiku 3 $0.50 · Gemma 2 27B $0.65 · DeepSeek R1 0528 $0.932 per 1M tokens (3:1 blend)
  • Longest contextClaude Haiku 3Claude Haiku 3 200,000 · DeepSeek R1 0528 163,840 · Gemma 2 27B 8,192 tokens
  • Widest inputsClaude Haiku 3Gemma 2 27B: Text · DeepSeek R1 0528: Text · Claude Haiku 3: Text, Images, PDFs
  • Self-hostingGemma 2 27B and DeepSeek R1 0528Publishes downloadable weights (MIT)
How the score is built
MeasureWeightGemma 2 27BDeepSeek R1 0528Claude Haiku 3
CapabilityCapabilities Index (ECI)50%486947
Price25%564961
Inputs & features15%03560
Context window10%03639
Overall100%38/10055/10052/100
02 — Side by side

Every spec in one table

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

Gemma 2 27B vs DeepSeek R1 0528 vs Claude Haiku 3 specifications side by side
SpecificationGemma 2 27BGoogleDeepSeek R1 0528DeepSeekClaude Haiku 3Anthropic
Capability
Capabilities Index (ECI)118.6140.8 (best)117.8
ECI rank#152 of 158#113 of 158 (best)#154 of 158
GPQA DiamondGraduate-level science questions36.5%76.3% (best)36.3%
OTIS Mock AIME 2024–2025Competition mathematics1.4%66.4% (best)1.8%
Price per million tokens
Input$0.65$0.512$0.25 (best)
Output$0.65 (best)$2.19$1.25
Cached input———
Blended (3:1)$0.65$0.932$0.50 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersMedian of 16 providersMedian of 3 providers
Limits
Context window8,192 tokens163,840 tokens200,000 tokens (best)
Max output2,048 tokens32,768 tokens (best)4,096 tokens
Inputs and features
TextYesYesYes
ImagesNoNoYes
PDFsNoNoYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoYesNo
Tool callingNoYesYes
Structured outputNoNoNo
Availability
WeightsOpenOpenMITProprietary
API model ID———
API providers316 (best)3
ReleasedJul 13, 2024May 28, 2025Mar 13, 2024
Knowledge cutoffJun 30, 2024—Aug 31, 2023
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.

  • Gemma 2 27B$7.80
  • DeepSeek R1 0528$9.50
  • Claude Haiku 3$5.00
04 — Questions

Which should you choose?

Which is better: Gemma 2 27B, DeepSeek R1 0528 or Claude Haiku 3?

DeepSeek R1 0528 is the better all-round choice, scoring 55/100 against Claude Haiku 3 (52) and Gemma 2 27B (38). It leads on capability. Claude Haiku 3 wins on price, inputs & features and context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Gemma 2 27B, DeepSeek R1 0528 or Claude Haiku 3?

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); DeepSeek R1 0528 costs $0.512 input / $2.19 output per million tokens (median across 16 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 $0.932 for DeepSeek R1 0528 (1.9× as much).

Which scores higher on benchmarks?

DeepSeek R1 0528 scores higher on the Capabilities Index (ECI): DeepSeek R1 0528 140.8 (#113 of 158), Gemma 2 27B 118.6 (#152 of 158) and Claude Haiku 3 117.8 (#154 of 158). Their confidence ranges do not overlap (138.9–142.5 vs 114.5–122.4), so the gap is a real one. On individual benchmarks: GPQA Diamond — DeepSeek R1 0528 76.3%, Gemma 2 27B 36.5%, Claude Haiku 3 36.3%; OTIS Mock AIME 2024–2025 — DeepSeek R1 0528 66.4%, Claude Haiku 3 1.8%, Gemma 2 27B 1.4%.

Which is better for coding?

There are no published SWE-bench Verified results for Gemma 2 27B, DeepSeek R1 0528 and Claude Haiku 3 yet, so there is no like-for-like coding score. On overall capability, DeepSeek R1 0528 leads, which tends to carry over to coding, but test on your own codebase. 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 163,840 for DeepSeek R1 0528 and 8,192 for Gemma 2 27B. Maximum output per response: Gemma 2 27B up to 2,048, DeepSeek R1 0528 up to 32,768, Claude Haiku 3 up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Gemma 2 27B accepts text; DeepSeek R1 0528 accepts text; Claude Haiku 3 accepts text, images and PDFs. Claude Haiku 3 handles the widest range of inputs.

Are any of these open source?

Gemma 2 27B and DeepSeek R1 0528 publishes its weights (MIT) and can be self-hosted; Claude Haiku 3 is proprietary.

Which is newer?

DeepSeek R1 0528 is the newest, released May 28, 2025. Gemma 2 27B came out Jul 13, 2024; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Gemma 2 27B Jun 30, 2024, Claude Haiku 3 Aug 31, 2023.

How do you decide the winner?

This rating uses 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 18, 2026.