Model Comparison

Sarvam-105B vs Sarvam-30BWhich is better in 2026?

Sarvam-105B significantly outperforms across most benchmarks.

Verdict: Sarvam-105B vs Sarvam-30B — which is better?

Sarvam-105B (by Sarvam AI) and Sarvam-30B (by Sarvam AI) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Sarvam-105B outperforms in 11 benchmarks (Arena-Hard v2, Beyond AIME, BrowseComp, GPQA, HMMT 2025, HMMT25, LiveCodeBench v6, MATH-500, MMLU, MMLU-Pro, SWE-Bench Verified), while Sarvam-30B is better at 0 benchmarks. Sarvam-105B significantly outperforms across most benchmarks.

Choose Sarvam-105B if…

  • you want the strongest raw capability — it leads on 11 of 12 shared benchmarks

Choose Sarvam-30B if…

  • you are already invested in the Sarvam AI ecosystem

Performance Benchmarks

Comparative analysis across standard metrics

12 benchmarks

Sarvam-105B outperforms in 11 benchmarks (Arena-Hard v2, Beyond AIME, BrowseComp, GPQA, HMMT 2025, HMMT25, LiveCodeBench v6, MATH-500, MMLU, MMLU-Pro, SWE-Bench Verified), while Sarvam-30B is better at 0 benchmarks.

Sarvam-105B significantly outperforms across most benchmarks.

Tue Jul 28 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

75.0B diff

Sarvam-105B has 75.0B more parameters than Sarvam-30B, making it 250.0% larger.

Sarvam AI
Sarvam-105B
105.0Bparameters
Sarvam AI
Sarvam-30B
30.0Bparameters
105.0B
Sarvam-105B
30.0B
Sarvam-30B

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

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

Sarvam-105B

Apache 2.0

Open weights

Sarvam-30B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Both models were released on 2026-03-06.

They likely represent similar generations of model development.

Sarvam-105B

Mar 6, 2026

4 months ago

Sarvam-30B

Mar 6, 2026

4 months ago

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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Sarvam AI
Higher Arena-Hard v2 score (71.0% vs 49.0%)
Higher Beyond AIME score (69.1% vs 58.3%)
Higher BrowseComp score (49.5% vs 35.5%)
Higher GPQA score (78.7% vs 66.5%)
Higher HMMT 2025 score (85.8% vs 73.3%)
Higher HMMT25 score (85.8% vs 74.2%)
Higher LiveCodeBench v6 score (71.7% vs 70.0%)
Higher MATH-500 score (98.6% vs 97.0%)
Higher MMLU score (90.6% vs 85.1%)
Higher MMLU-Pro score (81.7% vs 80.0%)
Higher SWE-Bench Verified score (45.0% vs 34.0%)
Sarvam AI

No standout differentiators in the data we have for this pair.

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against Sarvam-105B and Sarvam-30B side-by-side, then vote on the output you prefer.

Sarvam-105B
✓ Preferred
Sarvam-30B
Open in Playground
AI Model Comparison Table
Feature
Sarvam AI
Sarvam-105B
Sarvam AI
Sarvam-30B

FAQ

Common questions about Sarvam-105B vs Sarvam-30B.

Which is better, Sarvam-105B or Sarvam-30B?

Sarvam-105B significantly outperforms across most benchmarks. Sarvam-105B is made by Sarvam AI and Sarvam-30B is made by Sarvam AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Sarvam-105B compare to Sarvam-30B in benchmarks?

Sarvam-105B scores MATH-500: 98.6%, AIME 2025: 96.7%, MMLU: 90.6%, HMMT 2025: 85.8%, HMMT25: 85.8%. Sarvam-30B scores MATH-500: 97.0%, AIME 2025: 96.7%, MBPP: 92.7%, HumanEval: 92.1%, MMLU: 85.1%.

Related comparisons