The AI arena is free today

Open Superagent

Claude 3 Haiku vs Gemma 3 27B

Gemma 3 27B leads the LLM Stats Score 8.5 to -1.2. Gemma 3 27B is 4.0x cheaper per token.

Anthropic · Google · Updated for 2026

Which is better?

Gemma 3 27B leads the overall LLM Stats Score 8.5 to -1.2, ranking #268 overall.

In the 5 individual benchmarks reported for both models, Gemma 3 27B wins 5; this is a narrower head-to-head signal than the composite indexes.

On price, Gemma 3 27B is roughly 4.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Claude 3 Haiku also accepts a larger context window (200,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Claude 3 Haiku

  • you process long inputs — it offers a 200,000 token context window

Choose Gemma 3 27B

  • overall performance matters — it scores 8.5 and ranks #268 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 5 of 5 exact shared results
  • cost matters — it's about 4.0x cheaper per token
  • you want the most recent training data — it shipped Mar 2025
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
-1.2
#322
8.5
#268
-1.3
#314
8.8
#256
0.7
#229
5.5
#191
Cost, coverage & limits
Benchmark wins
0 of 5
5 of 5
Input price
$0.25 / M
$0.10 / M
Output price
$1.25 / M
$0.20 / M
Context window
200,000
131,072

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Claude 3 Haiku
Gemma 3 27B
4.7#272
17.7#185
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

10 reported for Claude 3 Haiku · 27 for Gemma 3 27B

5 shared

Claude 3 Haiku outperforms in 0 benchmarks, while Gemma 3 27B is better at 5 benchmarks (BIG-Bench Hard, GPQA, GSM8k, HumanEval, MATH).

Gemma 3 27B significantly outperforms across most benchmarks.

Thu Sep 03 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Gemma 3 27B costs less

For input processing, Claude 3 Haiku ($0.25/1M tokens) is 2.5x more expensive than Gemma 3 27B ($0.10/1M tokens).

For output processing, Claude 3 Haiku ($1.25/1M tokens) is 6.3x more expensive than Gemma 3 27B ($0.20/1M tokens).

In conclusion, Claude 3 Haiku is more expensive than Gemma 3 27B.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Thu Sep 03 2026 • llm-stats.com
Anthropic
Claude 3 Haiku
Input tokens$0.25
Output tokens$1.25
Best providerAnthropic
Google
Gemma 3 27B
Input tokens$0.10
Output tokens$0.20
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

Claude 3 Haiku accepts 200,000 input tokens compared to Gemma 3 27B's 131,072 tokens. Claude 3 Haiku can generate longer responses up to 200,000 tokens, while Gemma 3 27B is limited to 131,072 tokens.

Anthropic
Claude 3 Haiku
Input200,000 tokens
Output200,000 tokens
Google
Gemma 3 27B
Input131,072 tokens
Output131,072 tokens
Thu Sep 03 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Claude 3 Haiku and Gemma 3 27B support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Claude 3 Haiku

Text
Images
Audio
Video

Gemma 3 27B

Text
Images
Audio
Video

License

Usage and distribution terms

Claude 3 Haiku is licensed under a proprietary license, while Gemma 3 27B uses Gemma.

License differences may affect how you can use these models in commercial or open-source projects.

Claude 3 Haiku

Proprietary

Closed source

Gemma 3 27B

Gemma

Open weights

Release Timeline

When each model was launched

Claude 3 Haiku was released on 2024-03-13, while Gemma 3 27B was released on 2025-03-12.

Gemma 3 27B is 12 months newer than Claude 3 Haiku.

Claude 3 Haiku

Mar 13, 2024

2.5 years ago

Gemma 3 27B

Mar 12, 2025

1.5 years ago

12mo newer

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Claude 3 Haiku is available from Anthropic, Bedrock, Google. Gemma 3 27B is available from DeepInfra, Novita.

Claude 3 Haiku

anthropic logo
Anthropic
Input Price:Input: $0.25/1MOutput Price:Output: $1.25/1M
bedrock logo
AWS Bedrock
Input Price:Input: $0.25/1MOutput Price:Output: $1.25/1M
google logo
Google
Input Price:Input: $0.25/1MOutput Price:Output: $1.25/1M

Gemma 3 27B

deepinfra logo
Deepinfra
Input Price:Input: $0.10/1MOutput Price:Output: $0.20/1M
novita logo
Novita
Input Price:Input: $0.11/1MOutput Price:Output: $0.20/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Claude 3 Haiku and Gemma 3 27B side-by-side, then vote on the output you prefer.

Claude 3 Haiku
✓ Preferred
Gemma 3 27B
Open in Playground

FAQ

Common questions about Claude 3 Haiku vs Gemma 3 27B.

Which is better, Claude 3 Haiku or Gemma 3 27B?

Gemma 3 27B leads the LLM Stats Score 8.5 to -1.2. Claude 3 Haiku is made by Anthropic and Gemma 3 27B is made by Google. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude 3 Haiku compare to Gemma 3 27B in benchmarks?

Claude 3 Haiku scores ARC-C: 89.2%, GSM8k: 88.9%, HellaSwag: 85.9%, DROP: 78.4%, HumanEval: 75.9%. Gemma 3 27B scores GSM8k: 95.9%, IFEval: 90.4%, MATH: 89.0%, HumanEval: 87.8%, BIG-Bench Hard: 87.6%.

Is Claude 3 Haiku cheaper than Gemma 3 27B?

Gemma 3 27B is 2.5x cheaper for input tokens. Claude 3 Haiku costs $0.25/M input and $1.25/M output via anthropic. Gemma 3 27B costs $0.10/M input and $0.20/M output via deepinfra.

What are the context window sizes for Claude 3 Haiku and Gemma 3 27B?

Claude 3 Haiku supports 200K tokens and Gemma 3 27B supports 131K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Claude 3 Haiku and Gemma 3 27B?

Key differences include LLM Stats Score (-1.2 vs 8.5), context window (200K vs 131K), input pricing ($0.25 vs $0.10/M), licensing (Proprietary vs Gemma). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude 3 Haiku and Gemma 3 27B?

Claude 3 Haiku is developed by Anthropic and Gemma 3 27B is developed by Google.