The AI arena is free today

Open Superagent

Parse vs Sarvam-105B

Comparing Parse and Sarvam-105B across benchmarks, pricing, and capabilities.

Cohere · Sarvam AI · Updated for 2026

Which is better?

Parse and Sarvam-105B trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

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

Choose Parse

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

Choose Sarvam-105B

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

At a glance

The differences that matter most.

Parse
Cohere
Sarvam-105B
Sarvam AI
Benchmark wins
—
—
Input price
— / M
— / M
Output price
— / M
— / M
Context window
8,192
—

Individual benchmarks

1 reported for Parse · 14 for Sarvam-105B

No common benchmarks found

Parse and Sarvam-105Bdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

102.7B diff

Sarvam-105B has 102.7B more parameters than Parse, making it 4465.2% larger.

Cohere
Parse
2.3Bparameters
Sarvam AI
Sarvam-105B
105.0Bparameters
2.3B
Parse
105.0B
Sarvam-105B

Context Window

Maximum input and output token capacity

Only Parse specifies input context (8,192 tokens).

Cohere
Parse
Input8,192 tokens
Output- tokens
Sarvam AI
Sarvam-105B
Input- tokens
Output- tokens
Fri Sep 04 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Parse supports multimodal inputs, whereas Sarvam-105B does not.

Parse can handle both text and other forms of data like images, making it suitable for multimodal applications.

Parse

Text
Images
Audio
Video

Sarvam-105B

Text
Images
Audio
Video

License

Usage and distribution terms

Parse is licensed under a proprietary license, while Sarvam-105B uses Apache 2.0.

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

Parse

Proprietary

Closed source

Sarvam-105B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Parse was released on 2026-08-27, while Sarvam-105B was released on 2026-03-06.

Parse is 6 months newer than Sarvam-105B.

Parse

Aug 27, 2026

1 weeks ago

5mo newer
Sarvam-105B

Mar 6, 2026

6 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→

Judge for yourself.

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

Parse
✓ Preferred
Sarvam-105B
Open in Playground

FAQ

Common questions about Parse vs Sarvam-105B.

Which is better, Parse or Sarvam-105B?

Parse (Cohere) and Sarvam-105B (Sarvam AI) each have strengths in different areas. Compare their benchmark scores, pricing, context windows, and capabilities above to determine which fits your needs.

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

Parse scores ParseBench: 79.2%. 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 Parse and Sarvam-105B?

Parse supports 8K 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 Parse and Sarvam-105B?

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

Who makes Parse and Sarvam-105B?

Parse is developed by Cohere and Sarvam-105B is developed by Sarvam AI.

Related comparisons