Sarvam-105B: Benchmarks, Pricing & Context Window
Sarvam-105B is a language model from Unknown Organization, released in March 2026.
Sarvam-105B is Sarvam AI's flagship open-source Mixture-of-Experts reasoning model built for complex reasoning, coding, and agentic workflows. It uses 128 sparse experts with Multi-head Latent Attention for efficient long-context inference
Sarvam-105B benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Sarvam-105B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Sarvam-105B holds up as conversations get longer.
Quality Tracker
Sarvam-105B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sun Sep 13 2026Sarvam-105B model size
Sarvam-105B has 105 billion parameters and was trained on 12 trillion tokens. See how it compares to other models in the same parameter range.
Try now
huggleMake it with
Sarvam-105B.
Sarvam-105B latency
Sarvam-105B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Sarvam-105B examples
Recent arena outputs from Sarvam-105B, picked from the highest-ranked matchups.
Sarvam-105B license
Sarvam-105B is released under the Apache 2.0 license, which permits commercial use, has 105.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 105.0B
Apache License 2.0 - allows commercial use
Sarvam-105B resources
Official sources for Sarvam-105B: provider documentation, official playground, official launch post, model weights.
Sarvam-105B vs other models
The most-compared alternatives to Sarvam-105B are GPT-5.1 Codex High, o1-pro, Nova 2 Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Sarvam-105B
Models ranked just above and below Sarvam-105B by LLM Stats score.
FAQ
Common questions about Sarvam-105B.