# MiniMax M3 vs Sarvam 30B

> Side-by-side benchmark comparison for MiniMax M3 and Sarvam 30B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/minimax-m3-vs-sarvam-30b
- Last updated: October 15, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: MiniMax M3 and Sarvam 30B share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Sarvam 30B has the lower published output-token price.
- MiniMax M3 has the larger published context window at 1M.

## Model Snapshot

| Property | MiniMax M3 | Sarvam 30B |
|----------|----------|----------|
| Creator | MiniMax | Sarvam |
| Type | Open Weight | Open Weight |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 1M | 64K |
| Independent public score (not head-to-head) | 54.94 | 28.63 |
| Benchmarks Covered | 27 | 9 |
| Pricing (input/output) | $0.30 / $1.20 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- MiniMax M3 public-lane score: 39.4 (Supported · #67/126)
- Sarvam 30B public-lane score: Coming soon

| Benchmark | MiniMax M3 | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.1 | 66.0% | Coming soon | Coming soon |
| BrowseComp | 83.5% | 35.5% | MiniMax M3 |
| OSWorld-Verified | 70.1% | Coming soon | Coming soon |
| MCP Atlas | 74.2% | Coming soon | Coming soon |
| Claw-Eval | 74.5% | Coming soon | Coming soon |
| BankerToolBench | 76.1% | Coming soon | Coming soon |
| ResearchClawBench | 19.8% | Coming soon | Coming soon |
| OSWorld 2.0 | 4.6% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 53.6% | Coming soon | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- MiniMax M3 public-lane score: 36.5 (Supported · #73/149)
- Sarvam 30B public-lane score: Coming soon

| Benchmark | MiniMax M3 | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 80.5% | 34% | MiniMax M3 |
| SWE-bench Pro | 59% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | 66.0% | Coming soon | Coming soon |
| NL2Repo | 42.1% | Coming soon | Coming soon |
| VIBE V2 | 50.1% | Coming soon | Coming soon |
| SVG-Bench | 63.7% | Coming soon | Coming soon |
| KernelBench Hard | 28.8% | Coming soon | Coming soon |
| OpenHarmony Bench | 48.4% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 82.2% | Coming soon | Coming soon |
| SWE-bench (Vals) | 75.0% | Coming soon | Coming soon |
| HumanEval | Coming soon | 92.1% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- MiniMax M3 public-lane score: 82.9 (#5/29)
- Sarvam 30B public-lane score: 25.9 (Unranked · 3 rankable rows)

| Benchmark | MiniMax M3 | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond | Coming soon | 66.5% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- MiniMax M3 public-lane score: 61.5 (#43/54)
- Sarvam 30B public-lane score: Coming soon

| Benchmark | MiniMax M3 | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| OfficeQA Pro | 45.1% | Coming soon | Coming soon |
| OmniDocBench 1.5 | 91.6% | Coming soon | Coming soon |
| MMMU-Pro | 78.1% | Coming soon | Coming soon |
| VideoMMMU | 84.6% | Coming soon | Coming soon |
| Video-MME (with subtitle) | 85.4% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- MiniMax M3 public-lane score: 49.6 (Supported · #81/182)
- Sarvam 30B public-lane score: 27.4 (Supported · #163/182)

| Benchmark | MiniMax M3 | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 92.7% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 84.2% | Coming soon | Coming soon |
| MMLU | Coming soon | 85.1% | Coming soon |
| MMLU-Pro | Coming soon | 80% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- MiniMax M3 public-lane score: 93.8 (#5/146)
- Sarvam 30B public-lane score: 28.8 (#138/146)

### Mathematics

- Winner: Insufficient shared evidence
- MiniMax M3 public-lane score: Coming soon
- Sarvam 30B public-lane score: Coming soon

| Benchmark | MiniMax M3 | Sarvam 30B | Winner |
|-----------|-----------|-----------|--------|
| USAMO 2026 | 85.7% | Coming soon | Coming soon |
| 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 MiniMax M3 and Sarvam 30B?

Not yet. The models share only 2 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

- [MiniMax M3 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-minimax-m3)
- [Sarvam 30B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-sarvam-30b)
- [MiniMax M3 vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-minimax-m3)
- [Sarvam 30B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-sarvam-30b)

## Explore More

- [MiniMax M3 profile](/models/minimax-m3)
- [Sarvam 30B profile](/models/sarvam-30b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)