The AI arena is free today

Open Superagent

DiffusionGemma 26B-A4B vs Mercury 3

Mercury 3 leads the LLM Stats Score 36.1 to 19.0.

Google · Inception · Updated for 2026

Which is better?

Mercury 3 leads the overall LLM Stats Score 36.1 to 19.0, ranking #98 overall.

In the 2 individual benchmarks reported for both models, Mercury 3 wins 2; this is a narrower head-to-head signal than the composite indexes.

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

Choose DiffusionGemma 26B-A4B

  • you need open weights you can self-host or fine-tune

Choose Mercury 3

  • overall performance matters — it scores 36.1 and ranks #98 on LLM Stats
  • your work emphasizes reasoning and agents — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results
  • you want the most recent training data — it shipped Oct 2026

At a glance

The differences that matter most.

Core performance indexes
19.0
#230
36.1
#98
18.7
#228
34.8
#103
0.4
#197
19.4
#84
Cost, coverage & limits
Benchmark wins
0 of 2
2 of 2
Input price
— / M
$0.10 / M
Output price
— / M
$0.35 / M
Context window
—
1,000,000

Individual benchmarks

14 reported for DiffusionGemma 26B-A4B · 12 for Mercury 3

2 shared

DiffusionGemma 26B-A4B outperforms in 0 benchmarks, while Mercury 3 is better at 2 benchmarks (GPQA, MRCR v2).

Mercury 3 significantly outperforms across most benchmarks.

Mon Oct 26 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Mercury 3 specifies input context (1,000,000 tokens). Only Mercury 3 specifies output context (131,072 tokens).

Google
DiffusionGemma 26B-A4B
Input- tokens
Output- tokens
Inception
Mercury 3
Input1,000,000 tokens
Output131,072 tokens
Mon Oct 26 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

DiffusionGemma 26B-A4B supports multimodal inputs, whereas Mercury 3 does not.

DiffusionGemma 26B-A4B can handle both text and other forms of data like images, making it suitable for multimodal applications.

DiffusionGemma 26B-A4B

Text
Images
Audio
Video

Mercury 3

Text
Images
Audio
Video

License

Usage and distribution terms

DiffusionGemma 26B-A4B is licensed under Apache 2.0, while Mercury 3 uses a proprietary license.

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

DiffusionGemma 26B-A4B

Apache 2.0

Open weights

Mercury 3

Proprietary

Closed source

Release Timeline

When each model was launched

DiffusionGemma 26B-A4B was released on 2026-06-10, while Mercury 3 was released on 2026-10-19.

Mercury 3 is 4 months newer than DiffusionGemma 26B-A4B.

DiffusionGemma 26B-A4B

Jun 10, 2026

4 months ago

Mercury 3

Oct 19, 2026

6 days ago

4mo newer

Knowledge Cutoff

When training data ends

DiffusionGemma 26B-A4B has a documented knowledge cutoff of 2025-01-01, while Mercury 3's cutoff date is not specified.

We can confirm DiffusionGemma 26B-A4B's training data extends to 2025-01-01, but cannot make a direct comparison without Mercury 3's cutoff date.

DiffusionGemma 26B-A4B

Jan 2025

Mercury 3

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against DiffusionGemma 26B-A4B and Mercury 3 side-by-side, then vote on the output you prefer.

DiffusionGemma 26B-A4B
✓ Preferred
Mercury 3
Open in Playground

FAQ

Common questions about DiffusionGemma 26B-A4B vs Mercury 3.

Which is better, DiffusionGemma 26B-A4B or Mercury 3?

Mercury 3 leads the LLM Stats Score 36.1 to 19.0. DiffusionGemma 26B-A4B is made by Google and Mercury 3 is made by Inception. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does DiffusionGemma 26B-A4B compare to Mercury 3 in benchmarks?

DiffusionGemma 26B-A4B scores MMMLU: 81.5%, MMLU-Pro: 77.6%, GPQA: 73.2%, MathVision: 70.5%, AIME 2026: 69.1%. Mercury 3 scores GPQA: 89.2%, AA-LCR: 77.7%, IFBench: 76.8%, MRCR v2: 75.5%, DeepSearchQA: 71.3%.

What are the context window sizes for DiffusionGemma 26B-A4B and Mercury 3?

DiffusionGemma 26B-A4B supports an unknown number of tokens and Mercury 3 supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DiffusionGemma 26B-A4B and Mercury 3?

Key differences include LLM Stats Score (19.0 vs 36.1), multimodal support (yes vs no), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes DiffusionGemma 26B-A4B and Mercury 3?

DiffusionGemma 26B-A4B is developed by Google and Mercury 3 is developed by Inception.