ZMIME
Comparison · 3 models · Updated Nov 18, 2026

Gemma 2 27B vs GPT-4o mini vs Claude Haiku 3

GPT-4o mini comes out ahead, 58 to 52 and 38 on our weighted score, and it is the cheaper option too.

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

    OpenAI

    GPT-4o mini

    Released Jul 18, 2024

    58/100
    • ECI123.8
    • Price$0.15 / $0.60
    • Context128K
  3. Anthropic

    Claude Haiku 3

    Released Mar 13, 2024

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

GPT-4o mini is our pick

GPT-4o mini is the better all-round choice, scoring 58/100 against Claude Haiku 3 (52) and Gemma 2 27B (38). It leads on capability, price and inputs & features. Claude Haiku 3 wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGPT-4o miniCapabilities Index (ECI): GPT-4o mini 123.8 · Gemma 2 27B 118.6 · Claude Haiku 3 117.8
  • Lowest priceGPT-4o miniGPT-4o mini $0.263 · Claude Haiku 3 $0.50 · Gemma 2 27B $0.65 per 1M tokens (3:1 blend)
  • Longest contextClaude Haiku 3Claude Haiku 3 200,000 · GPT-4o mini 128,000 · Gemma 2 27B 8,192 tokens
  • Widest inputsGPT-4o mini and Claude Haiku 3Gemma 2 27B: Text · GPT-4o mini: Text, Images, PDFs · Claude Haiku 3: Text, Images, PDFs
  • Self-hostingGemma 2 27BPublishes downloadable weights
How the score is built
MeasureWeightGemma 2 27BGPT-4o miniClaude Haiku 3
CapabilityCapabilities Index (ECI)50%485347
Price25%567461
Inputs & features15%07060
Context window10%03239
Overall100%38/10058/10052/100
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 GPT-4o mini vs Claude Haiku 3 specifications side by side
SpecificationGemma 2 27BGoogleGPT-4o miniOpenAIClaude Haiku 3Anthropic
Capability
Capabilities Index (ECI)118.6123.8 (best)117.8
ECI rank#152 of 158#147 of 158 (best)#154 of 158
GPQA DiamondGraduate-level science questions36.5%37.7% (best)36.3%
FrontierMath Tiers 1–3Research-level mathematics—0.7%—
OTIS Mock AIME 2024–2025Competition mathematics1.4%6.9% (best)1.8%
SimpleQA VerifiedShort factual questions—8.3%—
Price per million tokens
Input$0.65$0.15 (best)$0.25
Output$0.65$0.60 (best)$1.25
Cached input—$0.075—
Blended (3:1)$0.65$0.263 (best)$0.50
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersOfficial OpenAI APIMedian of 3 providers
Limits
Context window8,192 tokens128,000 tokens200,000 tokens (best)
Max output2,048 tokens16,384 tokens (best)4,096 tokens
Inputs and features
TextYesYesYes
ImagesNoYesYes
PDFsNoYesYes
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingNoYesYes
Structured outputNoYesNo
Availability
WeightsOpenProprietaryProprietary
API model ID—gpt-4o-mini—
API providers327 (best)3
ReleasedJul 13, 2024Jul 18, 2024Mar 13, 2024
Knowledge cutoffJun 30, 2024Sep 2023Aug 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
  • GPT-4o mini$2.70
  • Claude Haiku 3$5.00
04 — Questions

Which should you choose?

Which is better: Gemma 2 27B, GPT-4o mini or Claude Haiku 3?

GPT-4o mini is the better all-round choice, scoring 58/100 against Claude Haiku 3 (52) and Gemma 2 27B (38). It leads on capability, price and inputs & features. Claude Haiku 3 wins on context window. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Gemma 2 27B, GPT-4o mini or Claude Haiku 3?

GPT-4o mini is cheaper at $0.15 input / $0.60 output per million tokens (official OpenAI API price). Claude Haiku 3 costs $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). At a typical mix of three input tokens to one output token, that is $0.263 per million tokens for GPT-4o mini versus $0.50 for Claude Haiku 3 (1.9× as much) and $0.65 for Gemma 2 27B (2.5× as much).

Which scores higher on benchmarks?

GPT-4o mini scores higher on the Capabilities Index (ECI): GPT-4o mini 123.8 (#147 of 158), Gemma 2 27B 118.6 (#152 of 158) and Claude Haiku 3 117.8 (#154 of 158). The confidence ranges of the top two overlap (120.5–126.7 vs 114.5–122.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — GPT-4o mini 37.7%, Gemma 2 27B 36.5%, Claude Haiku 3 36.3%; OTIS Mock AIME 2024–2025 — GPT-4o mini 6.9%, 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, GPT-4o mini and Claude Haiku 3 yet, so there is no like-for-like coding score. On overall capability, GPT-4o mini 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 128,000 for GPT-4o mini and 8,192 for Gemma 2 27B. Maximum output per response: Gemma 2 27B up to 2,048, GPT-4o mini up to 16,384, Claude Haiku 3 up to 4,096 tokens.

Which can read images, PDFs, audio or video?

Gemma 2 27B accepts text; GPT-4o mini accepts text, images and PDFs; Claude Haiku 3 accepts text, images and PDFs. GPT-4o mini handles the widest range of inputs.

Are any of these open source?

Gemma 2 27B publishes its weights and can be self-hosted; GPT-4o mini and Claude Haiku 3 is proprietary.

Which is newer?

GPT-4o mini is the newest, released Jul 18, 2024. Gemma 2 27B came out Jul 13, 2024; Claude Haiku 3 came out Mar 13, 2024. Knowledge cutoff: Gemma 2 27B Jun 30, 2024, GPT-4o mini Sep 2023, 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.