# Qwen3.5-122B-A10B vs Sarvam 30B

> Side-by-side benchmark comparison for Qwen3.5-122B-A10B and Sarvam 30B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/qwen3-5-122b-a10b-vs-sarvam-30b
- Last updated: November 11, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Qwen3.5-122B-A10B and Sarvam 30B share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Qwen3.5-122B-A10B has the larger published context window at 262K.

## Model Snapshot

| Property | Qwen3.5-122B-A10B | Sarvam 30B |
|----------|----------|----------|
| Creator | Alibaba | Sarvam |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 262K | 64K |
| Independent public score (not head-to-head) | 52.64 | 23.64 |
| Benchmarks Covered | 18 | 9 |
| Pricing (input/output) | $0.00 / $0.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Qwen3.5-122B-A10B public-lane score: 33.4 (Estimated · #95/132)
- Sarvam 30B public-lane score: Coming soon

| Benchmark | Qwen3.5-122B-A10B | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 49.4% | Coming soon | Coming soon |
| BrowseComp | 63.8% | 35.5% | Qwen3.5-122B-A10B |
| OSWorld-Verified | 58% | Coming soon | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Qwen3.5-122B-A10B public-lane score: 35.4 (Supported · #87/158)
- Sarvam 30B public-lane score: Coming soon

| Benchmark | Qwen3.5-122B-A10B | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 72% | 34% | Qwen3.5-122B-A10B |
| LiveCodeBench v6 | 78.9% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 49.4% | Coming soon | Coming soon |
| HumanEval | Coming soon | 92.1% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Qwen3.5-122B-A10B public-lane score: 40.2 (Supported · #81/158)
- Sarvam 30B public-lane score: 21.4 (Estimated · #148/158)

| Benchmark | Qwen3.5-122B-A10B | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | 60.2% | Coming soon | Coming soon |
| GPQA Diamond | Coming soon | 66.5% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Qwen3.5-122B-A10B public-lane score: 51.4 (Estimated · #52/67)
- Sarvam 30B public-lane score: Coming soon

| Benchmark | Qwen3.5-122B-A10B | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| MMMU | 83.9% | Coming soon | Coming soon |
| MMVU | 74.7% | Coming soon | Coming soon |
| MMMU-Pro | 76.9% | Coming soon | Coming soon |
| MathVision | 86.2% | Coming soon | Coming soon |
| CharXiv | 77.2% | Coming soon | Coming soon |
| V* | 93.2% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Qwen3.5-122B-A10B public-lane score: 48 (Estimated · #89/179)
- Sarvam 30B public-lane score: 27.4 (Supported · #165/179)

| Benchmark | Qwen3.5-122B-A10B | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | 86.7% | 80% | Qwen3.5-122B-A10B |
| SuperGPQA | 67.1% | Coming soon | Coming soon |
| GPQA | 86.6% | Coming soon | Coming soon |
| MMLU | Coming soon | 85.1% | Coming soon |

### Multilingual

- Winner: Insufficient shared evidence
- Qwen3.5-122B-A10B public-lane score: 87.1 (#9/17)
- Sarvam 30B public-lane score: Coming soon

| Benchmark | Qwen3.5-122B-A10B | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | 82.2% | Coming soon | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- Qwen3.5-122B-A10B public-lane score: 93 (#13/157)
- Sarvam 30B public-lane score: 28.8 (#148/157)

| Benchmark | Qwen3.5-122B-A10B | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | 93.4% | Coming soon | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Qwen3.5-122B-A10B public-lane score: Coming soon
- Sarvam 30B public-lane score: Coming soon

| Benchmark | Qwen3.5-122B-A10B | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| MATH-500 | Coming soon | 97% | Coming soon |
| HMMT Feb 2025 | Coming soon | 73.3% | Coming soon |
| HMMT Nov 2025 | Coming soon | 74.2% | Coming soon |

## FAQ

### Is there enough evidence to pick between Qwen3.5-122B-A10B and Sarvam 30B?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [Qwen3.5-122B-A10B vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-qwen3-5-122b-a10b)
- [Sarvam 30B vs Claude Fable 5.2](/compare/claude-fable-5-2-vs-sarvam-30b)
- [Qwen3.5-122B-A10B vs Gemini 4 Carbon](/compare/gemini-4-carbon-vs-qwen3-5-122b-a10b)
- [Sarvam 30B vs Gemini 4 Carbon](/compare/gemini-4-carbon-vs-sarvam-30b)

## Explore More

- [Qwen3.5-122B-A10B profile](/models/qwen3-5-122b-a10b)
- [Sarvam 30B profile](/models/sarvam-30b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)