ZMIME
Comparison · 3 models · Updated Nov 2, 2026

Claude Haiku 3 vs Gemma 2 27B vs Mixtral 8x7B Instruct v0.1

Claude Haiku 3 comes out ahead, 46 to 35 and 34 on our weighted score.

  1. Our pick

    Anthropic

    Claude Haiku 3

    Released Mar 13, 2024

    46/100
    • ECI118.8
    • Price$0.25 / $1.25
    • Context200K
    Full specs Remove Claude Haiku 3

  2. Google

    Gemma 2 27B

    Released Jul 13, 2024

    35/100
    • ECI122.1
    • Price$0.65 / $0.65
    • Context8K
    Full specs Remove Gemma 2 27B

  3. Mistral AI

    Mixtral 8x7B Instruct v0.1

    Released Dec 11, 2023

    34/100
    • ECI118.4
    • Price$0.444 / $0.579
    • Context33K
    Full specs Remove Mixtral 8x7B Instruct v0.1
01 — Verdict

Claude Haiku 3 is our pick

Claude Haiku 3 is the better all-round choice, scoring 46/100 against Gemma 2 27B (35) and Mixtral 8x7B Instruct v0.1 (34). It leads on inputs & features and context window. Gemma 2 27B wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

  • CapabilityGemma 2 27BCapabilities Index (ECI): Gemma 2 27B 122.1 · Claude Haiku 3 118.8 · Mixtral 8x7B Instruct v0.1 118.4
  • Lowest priceMixtral 8x7B Instruct v0.1Mixtral 8x7B Instruct v0.1 $0.478 · Claude Haiku 3 $0.50 · Gemma 2 27B $0.65 per 1M tokens (3:1 blend)
  • Longest contextClaude Haiku 3Claude Haiku 3 200,000 · Mixtral 8x7B Instruct v0.1 32,768 · Gemma 2 27B 8,192 tokens
  • Widest inputsClaude Haiku 3Claude Haiku 3: Text, Images, PDFs · Gemma 2 27B: Text · Mixtral 8x7B Instruct v0.1: Text
  • Self-hostingGemma 2 27B and Mixtral 8x7B Instruct v0.1Publishes downloadable weights (Apache 2.0)
How the score is built
MeasureWeightClaude Haiku 3Gemma 2 27BMixtral 8x7B Instruct v0.1
CapabilityCapabilities Index (ECI)50%384238
Price25%615662
Inputs & features15%6000
Context window10%3200
Overall100%46/10035/10034/100
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 Gemma 2 27B vs Mixtral 8x7B Instruct v0.1 specifications side by side
SpecificationClaude Haiku 3AnthropicGemma 2 27BGoogleMixtral 8x7B Instruct v0.1Mistral AI
Capability
Capabilities Index (ECI)118.8122.1 (best)118.4
ECI rank#156 of 165#152 of 165 (best)#160 of 165
GPQA DiamondGraduate-level science questions36.3%36.5% (best)30.6%
OTIS Mock AIME 2024–2025Competition mathematics1.8% (best)1.4%—
Price per million tokens
Input$0.25 (best)$0.65$0.444
Output$1.25$0.65$0.579 (best)
Cached input———
Blended (3:1)$0.50$0.65$0.478 (best)
Long-context rateSame rateSame rateSame rate
Price sourceMedian of 3 providersMedian of 3 providersMedian of 2 providers
Limits
Context window200,000 tokens (best)8,192 tokens32,768 tokens
Max output4,096 tokens2,048 tokens32,768 tokens (best)
Inputs and features
TextYesYesYes
ImagesYesNoNo
PDFsYesNoNo
AudioNoNoNo
VideoNoNoNo
ReasoningNoNoNo
Tool callingYesNoNo
Structured outputNoNoNo
Availability
WeightsProprietaryOpenOpenApache 2.0
API model ID———
API providers3 (best)3 (best)2
ReleasedMar 13, 2024Jul 13, 2024Dec 11, 2023
Knowledge cutoffAug 31, 2023Jun 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
  • Gemma 2 27B$7.80
  • Mixtral 8x7B Instruct v0.1$5.60
04 — Questions

Which should you choose?

Which is better: Claude Haiku 3, Gemma 2 27B or Mixtral 8x7B Instruct v0.1?

Claude Haiku 3 is the better all-round choice, scoring 46/100 against Gemma 2 27B (35) and Mixtral 8x7B Instruct v0.1 (34). It leads on inputs & features and context window. Gemma 2 27B wins on capability. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.

Which is cheaper, Claude Haiku 3, Gemma 2 27B or Mixtral 8x7B Instruct v0.1?

Mixtral 8x7B Instruct v0.1 is cheaper at $0.444 input / $0.579 output per million tokens (median across 2 API providers). 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 $0.478 per million tokens for Mixtral 8x7B Instruct v0.1 versus $0.50 for Claude Haiku 3 (1× as much) and $0.65 for Gemma 2 27B (1.4× as much).

Which scores higher on benchmarks?

Gemma 2 27B scores higher on the Capabilities Index (ECI): Gemma 2 27B 122.1 (#152 of 165), Claude Haiku 3 118.8 (#156 of 165) and Mixtral 8x7B Instruct v0.1 118.4 (#160 of 165). The confidence ranges of the top two overlap (115.8–124.1 vs 111.7–121.4), so treat the gap as small. On individual benchmarks: GPQA Diamond — Gemma 2 27B 36.5%, Claude Haiku 3 36.3%, Mixtral 8x7B Instruct v0.1 30.6%.

Which is better for coding?

There are no published SWE-bench Verified results for Claude Haiku 3, Gemma 2 27B and Mixtral 8x7B Instruct v0.1 yet, so there is no like-for-like coding score. On overall capability, Gemma 2 27B leads, which tends to carry over to coding, but test on your own codebase. Note that Gemma 2 27B and Mixtral 8x7B Instruct v0.1 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 32,768 for Mixtral 8x7B Instruct v0.1 and 8,192 for Gemma 2 27B. Maximum output per response: Claude Haiku 3 up to 4,096, Gemma 2 27B up to 2,048, Mixtral 8x7B Instruct v0.1 up to 32,768 tokens.

Which can read images, PDFs, audio or video?

Claude Haiku 3 accepts text, images and PDFs; Gemma 2 27B accepts text; Mixtral 8x7B Instruct v0.1 accepts text. Claude Haiku 3 handles the widest range of inputs.

Are any of these open source?

Gemma 2 27B and Mixtral 8x7B Instruct v0.1 publishes its weights (Apache 2.0) and can be self-hosted; Claude Haiku 3 is proprietary.

Which is newer?

Gemma 2 27B is the newest, released Jul 13, 2024. Claude Haiku 3 came out Mar 13, 2024; Mixtral 8x7B Instruct v0.1 came out Dec 11, 2023. Knowledge cutoff: Claude Haiku 3 Aug 31, 2023, Gemma 2 27B Jun 30, 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