The AI arena is free today

Open Superagent

Qwen3 VL 235B A22B Instruct vs Sarvam-105B

Qwen3 VL 235B A22B Instruct and Sarvam-105B are closely matched at 24.7 and 25.7 on the LLM Stats Score.

Alibaba Cloud / Qwen Team · Sarvam AI · Updated for 2026

Which is better?

Qwen3 VL 235B A22B Instruct and Sarvam-105B are closely matched on the overall LLM Stats Score at 24.7 and 25.7.

In the 7 individual benchmarks reported for both models, Sarvam-105B wins 4; this is a narrower head-to-head signal than the composite indexes.

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

Choose Qwen3 VL 235B A22B Instruct

  • you want predictable pricing at $0.20/M input and $0.88/M output

Choose Sarvam-105B

  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 7 exact shared results
  • you want the most recent training data — it shipped Mar 2026

At a glance

The differences that matter most.

Core performance indexes
24.7
#161
25.7
#152
22.5
#169
26.2
#147
12.7
#99
5.6
#144
Cost, coverage & limits
Benchmark wins
3 of 7
4 of 7
Input price
$0.20 / M
— / M
Output price
$0.88 / M
— / M
Context window
262,144

Capability indexes

Additional strengths measured across groups of related public benchmarks

3 shared
Index
Qwen3 VL 235B A22B Instruct
Sarvam-105B
23.8#124
29.1#88
25.9#54
26.4#45
27.0#29
26.4#34
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

50 reported for Qwen3 VL 235B A22B Instruct · 14 for Sarvam-105B

7 shared

Qwen3 VL 235B A22B Instruct outperforms in 3 benchmarks (Arena-Hard v2, IFEval, MMLU-Pro), while Sarvam-105B is better at 4 benchmarks (AIME 2025, HMMT25, LiveCodeBench v6, MMLU).

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

Sun Sep 13 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

131.0B diff

Qwen3 VL 235B A22B Instruct has 131.0B more parameters than Sarvam-105B, making it 124.8% larger.

Alibaba Cloud / Qwen Team
Qwen3 VL 235B A22B Instruct
236.0Bparameters
Sarvam AI
Sarvam-105B
105.0Bparameters
236.0B
Qwen3 VL 235B A22B Instruct
105.0B
Sarvam-105B

Context Window

Maximum input and output token capacity

Only Qwen3 VL 235B A22B Instruct specifies input context (262,144 tokens). Only Qwen3 VL 235B A22B Instruct specifies output context (262,144 tokens).

Alibaba Cloud / Qwen Team
Qwen3 VL 235B A22B Instruct
Input262,144 tokens
Output262,144 tokens
Sarvam AI
Sarvam-105B
Input- tokens
Output- tokens
Sun Sep 13 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Qwen3 VL 235B A22B Instruct supports multimodal inputs, whereas Sarvam-105B does not.

Qwen3 VL 235B A22B Instruct can handle both text and other forms of data like images, making it suitable for multimodal applications.

Qwen3 VL 235B A22B Instruct

Text
Images
Audio
Video

Sarvam-105B

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under Apache 2.0.

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

Qwen3 VL 235B A22B Instruct

Apache 2.0

Open weights

Sarvam-105B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Qwen3 VL 235B A22B Instruct was released on 2025-09-22, while Sarvam-105B was released on 2026-03-06.

Sarvam-105B is 6 months newer than Qwen3 VL 235B A22B Instruct.

Qwen3 VL 235B A22B Instruct

Sep 22, 2025

11 months ago

Sarvam-105B

Mar 6, 2026

6 months ago

5mo 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 Qwen3 VL 235B A22B Instruct and Sarvam-105B side-by-side, then vote on the output you prefer.

Qwen3 VL 235B A22B Instruct
✓ Preferred
Sarvam-105B
Open in Playground

FAQ

Common questions about Qwen3 VL 235B A22B Instruct vs Sarvam-105B.

Which is better, Qwen3 VL 235B A22B Instruct or Sarvam-105B?

Qwen3 VL 235B A22B Instruct and Sarvam-105B are closely matched on the LLM Stats Score at 24.7 and 25.7. Qwen3 VL 235B A22B Instruct is made by Alibaba Cloud / Qwen Team 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 Qwen3 VL 235B A22B Instruct compare to Sarvam-105B in benchmarks?

Qwen3 VL 235B A22B Instruct scores DocVQAtest: 97.1%, ScreenSpot: 95.4%, MMLU-Redux: 92.2%, OCRBench: 92.0%, MMBench-V1.1: 89.9%. 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 Qwen3 VL 235B A22B Instruct and Sarvam-105B?

Qwen3 VL 235B A22B Instruct supports 262K 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 Qwen3 VL 235B A22B Instruct and Sarvam-105B?

Key differences include LLM Stats Score (24.7 vs 25.7), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.

Who makes Qwen3 VL 235B A22B Instruct and Sarvam-105B?

Qwen3 VL 235B A22B Instruct is developed by Alibaba Cloud / Qwen Team and Sarvam-105B is developed by Sarvam AI.