The AI arena is free today

Open Superagent

MiniMax M2 vs Sarvam-105B

MiniMax M2 and Sarvam-105B are closely matched at 26.8 and 25.7 on the LLM Stats Score.

MiniMax · Sarvam AI · Updated for 2026

Which is better?

MiniMax M2 and Sarvam-105B are closely matched on the overall LLM Stats Score at 26.8 and 25.7.

The models split the 6 individual benchmarks reported for both models evenly.

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

Choose MiniMax M2

  • your work emphasizes coding — it leads those capability indexes

Choose Sarvam-105B

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

At a glance

The differences that matter most.

Core performance indexes
26.8
#149
25.7
#157
26.5
#149
26.2
#151
18.0
#116
-1.6
#251
9.4
#127
5.5
#148
Cost, coverage & limits
Benchmark wins
3 of 6
3 of 6
Input price
$0.30 / M
— / M
Output price
$1.20 / M
— / M
Context window
1,000,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
MiniMax M2
Sarvam-105B
19.7#162
29.1#88
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

16 reported for MiniMax M2 · 14 for Sarvam-105B

6 shared

MiniMax M2 outperforms in 3 benchmarks (Humanity's Last Exam, MMLU-Pro, SWE-Bench Verified), while Sarvam-105B is better at 3 benchmarks (AIME 2025, BrowseComp, GPQA).

Both models are evenly matched across the benchmarks.

Tue Sep 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

125.0B diff

MiniMax M2 has 125.0B more parameters than Sarvam-105B, making it 119.0% larger.

MiniMax
MiniMax M2
230.0Bparameters
Sarvam AI
Sarvam-105B
105.0Bparameters
230.0B
MiniMax M2
105.0B
Sarvam-105B

Context Window

Maximum input and output token capacity

Only MiniMax M2 specifies input context (1,000,000 tokens). Only MiniMax M2 specifies output context (1,000,000 tokens).

MiniMax
MiniMax M2
Input1,000,000 tokens
Output1,000,000 tokens
Sarvam AI
Sarvam-105B
Input- tokens
Output- tokens
Tue Sep 22 2026 • llm-stats.com

License

Usage and distribution terms

MiniMax M2 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.

MiniMax M2

MIT

Open weights

Sarvam-105B

Apache 2.0

Open weights

Release Timeline

When each model was launched

MiniMax M2 was released on 2025-10-27, while Sarvam-105B was released on 2026-03-06.

Sarvam-105B is 4 months newer than MiniMax M2.

MiniMax M2

Oct 27, 2025

11 months ago

Sarvam-105B

Mar 6, 2026

6 months ago

4mo 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

Judge for yourself.

Run your own prompts against MiniMax M2 and Sarvam-105B side-by-side, then vote on the output you prefer.

MiniMax M2
✓ Preferred
Sarvam-105B
Open in Playground

FAQ

Common questions about MiniMax M2 vs Sarvam-105B.

Which is better, MiniMax M2 or Sarvam-105B?

MiniMax M2 and Sarvam-105B are closely matched on the LLM Stats Score at 26.8 and 25.7. MiniMax M2 is made by MiniMax 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 MiniMax M2 compare to Sarvam-105B in benchmarks?

MiniMax M2 scores Tau2 Telecom: 87.0%, LiveCodeBench: 83.0%, MMLU-Pro: 82.0%, AIME 2025: 78.0%, GPQA: 78.0%. 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 MiniMax M2 and Sarvam-105B?

MiniMax M2 supports 1.0M 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 MiniMax M2 and Sarvam-105B?

Key differences include LLM Stats Score (26.8 vs 25.7), licensing (MIT vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes MiniMax M2 and Sarvam-105B?

MiniMax M2 is developed by MiniMax and Sarvam-105B is developed by Sarvam AI.