Model Comparison

DeepSeek-R1-0528 vs Sarvam-105BWhich is better in 2026?

Sarvam-105B has a slight edge in benchmark performance.

Verdict: DeepSeek-R1-0528 vs Sarvam-105B — which is better?

DeepSeek-R1-0528 (by DeepSeek) and Sarvam-105B (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.

DeepSeek-R1-0528 outperforms in 3 benchmarks (GPQA, Humanity's Last Exam, MMLU-Pro), while Sarvam-105B is better at 4 benchmarks (AIME 2025, BrowseComp, HMMT 2025, SWE-Bench Verified). Sarvam-105B has a slight edge in benchmark performance.

Choose DeepSeek-R1-0528 if…

  • you want predictable pricing at $0.50/M input and $2.15/M output

Choose Sarvam-105B if…

  • you want the strongest raw capability — it leads on 4 of 7 shared benchmarks
  • you want the most recent training data — it shipped Mar 2026

Performance Benchmarks

Comparative analysis across standard metrics

7 benchmarks

DeepSeek-R1-0528 outperforms in 3 benchmarks (GPQA, Humanity's Last Exam, MMLU-Pro), while Sarvam-105B is better at 4 benchmarks (AIME 2025, BrowseComp, HMMT 2025, SWE-Bench Verified).

Sarvam-105B has a slight edge in benchmark performance.

Tue Jul 21 2026 • llm-stats.com

Arena Performance

Human preference votes

Model Size

Parameter count comparison

566.0B diff

DeepSeek-R1-0528 has 566.0B more parameters than Sarvam-105B, making it 539.0% larger.

DeepSeek
DeepSeek-R1-0528
671.0Bparameters
Sarvam AI
Sarvam-105B
105.0Bparameters
671.0B
DeepSeek-R1-0528
105.0B
Sarvam-105B

Context Window

Maximum input and output token capacity

Only DeepSeek-R1-0528 specifies input context (131,072 tokens). Only DeepSeek-R1-0528 specifies output context (131,072 tokens).

DeepSeek
DeepSeek-R1-0528
Input131,072 tokens
Output131,072 tokens
Sarvam AI
Sarvam-105B
Input- tokens
Output- tokens
Tue Jul 21 2026 • llm-stats.com

License

Usage and distribution terms

DeepSeek-R1-0528 is licensed under MIT, while Sarvam-105B uses Apache 2.0.

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

DeepSeek-R1-0528

MIT

Open weights

Sarvam-105B

Apache 2.0

Open weights

Release Timeline

When each model was launched

DeepSeek-R1-0528 was released on 2025-05-28, while Sarvam-105B was released on 2026-03-06.

Sarvam-105B is 9 months newer than DeepSeek-R1-0528.

DeepSeek-R1-0528

May 28, 2025

1.1 years ago

Sarvam-105B

Mar 6, 2026

4 months ago

9mo 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

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

DeepSeek
Larger context window (131,072 tokens)
Higher GPQA score (81.0% vs 78.7%)
Higher Humanity's Last Exam score (17.7% vs 11.2%)
Higher MMLU-Pro score (85.0% vs 81.7%)
Sarvam AI
Higher AIME 2025 score (96.7% vs 87.5%)
Higher BrowseComp score (49.5% vs 8.9%)
Higher HMMT 2025 score (85.8% vs 79.4%)
Higher SWE-Bench Verified score (45.0% vs 44.6%)

Detailed Comparison

Interactive Arena

Judge for yourself.

Run your own prompts against DeepSeek-R1-0528 and Sarvam-105B side-by-side, then vote on the output you prefer.

DeepSeek-R1-0528
✓ Preferred
Sarvam-105B
Open in Playground
AI Model Comparison Table
Feature
DeepSeek
DeepSeek-R1-0528
Sarvam AI
Sarvam-105B

FAQ

Common questions about DeepSeek-R1-0528 vs Sarvam-105B.

Which is better, DeepSeek-R1-0528 or Sarvam-105B?

Sarvam-105B has a slight edge in benchmark performance. DeepSeek-R1-0528 is made by DeepSeek and Sarvam-105B is made by Sarvam AI. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does DeepSeek-R1-0528 compare to Sarvam-105B in benchmarks?

DeepSeek-R1-0528 scores MMLU-Redux: 93.4%, SimpleQA: 92.3%, AIME 2024: 91.4%, AIME 2025: 87.5%, MMLU-Pro: 85.0%. Sarvam-105B scores MATH-500: 98.6%, AIME 2025: 96.7%, MMLU: 90.6%, HMMT 2025: 85.8%, HMMT25: 85.8%.

What are the context window sizes for DeepSeek-R1-0528 and Sarvam-105B?

DeepSeek-R1-0528 supports 131K tokens and Sarvam-105B supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between DeepSeek-R1-0528 and Sarvam-105B?

Key differences include licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes DeepSeek-R1-0528 and Sarvam-105B?

DeepSeek-R1-0528 is developed by DeepSeek and Sarvam-105B is developed by Sarvam AI.

Related comparisons