The AI arena is free today

Open Superagent

Gemma 4 12B vs Sarvam-105B

Gemma 4 12B and Sarvam-105B are closely matched at 22.0 and 25.7 on the LLM Stats Score.

Google · Sarvam AI · Updated for 2026

Which is better?

Gemma 4 12B and Sarvam-105B are closely matched on the overall LLM Stats Score at 22.0 and 25.7.

The models split the 4 individual benchmarks reported for both models evenly.

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

Choose Gemma 4 12B

  • you want the most recent training data — it shipped May 2026

Choose Sarvam-105B

  • you are already invested in the Sarvam AI ecosystem

At a glance

The differences that matter most.

Core performance indexes
22.0
#179
25.7
#152
23.0
#166
26.2
#147
Cost, coverage & limits
Benchmark wins
2 of 4
2 of 4
Input price
— / M
— / M
Output price
— / M
— / M
Context window

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Gemma 4 12B
Sarvam-105B
18.4#181
29.1#88
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

15 reported for Gemma 4 12B · 14 for Sarvam-105B

4 shared

Gemma 4 12B outperforms in 2 benchmarks (GPQA, LiveCodeBench v6), while Sarvam-105B is better at 2 benchmarks (Humanity's Last Exam, MMLU-Pro).

Both models are evenly matched across the benchmarks.

Fri Sep 11 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

93.0B diff

Sarvam-105B has 93.0B more parameters than Gemma 4 12B, making it 777.9% larger.

Google
Gemma 4 12B
12.0Bparameters
Sarvam AI
Sarvam-105B
105.0Bparameters
12.0B
Gemma 4 12B
105.0B
Sarvam-105B

Input capabilities

Documented input modalities across available providers

Gemma 4 12B supports multimodal inputs, whereas Sarvam-105B does not.

Gemma 4 12B can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemma 4 12B

Text
Images
Audio
Video

Sarvam-105B

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

Both models share the same licensing terms, providing consistent usage rights.

Gemma 4 12B

Apache 2.0

Open weights

Sarvam-105B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Gemma 4 12B was released on 2026-05-23, while Sarvam-105B was released on 2026-03-06.

Gemma 4 12B is 3 months newer than Sarvam-105B.

Gemma 4 12B

May 23, 2026

3 months ago

2mo newer
Sarvam-105B

Mar 6, 2026

6 months ago

Knowledge Cutoff

When training data ends

Gemma 4 12B has a documented knowledge cutoff of 2025-01-01, while Sarvam-105B's cutoff date is not specified.

We can confirm Gemma 4 12B's training data extends to 2025-01-01, but cannot make a direct comparison without Sarvam-105B's cutoff date.

Gemma 4 12B

Jan 2025

Sarvam-105B

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Gemma 4 12B and Sarvam-105B side-by-side, then vote on the output you prefer.

Gemma 4 12B
✓ Preferred
Sarvam-105B
Open in Playground

FAQ

Common questions about Gemma 4 12B vs Sarvam-105B.

Which is better, Gemma 4 12B or Sarvam-105B?

Gemma 4 12B and Sarvam-105B are closely matched on the LLM Stats Score at 22.0 and 25.7. Gemma 4 12B is made by Google and Sarvam-105B is made by Sarvam AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Gemma 4 12B compare to Sarvam-105B in benchmarks?

Gemma 4 12B scores FLEURS: 93.1%, MMMLU: 83.4%, MathVision: 79.7%, GPQA: 78.8%, AIME 2026: 77.5%. Sarvam-105B scores MATH-500: 98.6%, AIME 2025: 96.7%, MMLU: 90.6%, HMMT 2025: 85.8%, HMMT25: 85.8%.

What are the main differences between Gemma 4 12B and Sarvam-105B?

Key differences include LLM Stats Score (22.0 vs 25.7), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemma 4 12B and Sarvam-105B?

Gemma 4 12B is developed by Google and Sarvam-105B is developed by Sarvam AI.