# Kimi K2.6 vs Soofi S 30B-A3B

> Side-by-side benchmark comparison for Kimi K2.6 and Soofi S 30B-A3B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/kimi-2-6-vs-soofi-s-30b-a3b
- Last updated: October 14, 2026

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

## Quick Verdict

Evidence is too thin for a benchmark verdict: Kimi K2.6 and Soofi S 30B-A3B 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.
- Soofi S 30B-A3B has the lower published output-token price.
- Soofi S 30B-A3B has the larger published context window at 1M.

## Model Snapshot

| Property | Kimi K2.6 | Soofi S 30B-A3B |
|----------|----------|----------|
| Creator | Moonshot AI | Soofi Project |
| Type | Open Weight | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 256K | 1M |
| Independent public score (not head-to-head) | 58.47 | null |
| Benchmarks Covered | 37 | 8 |
| Pricing (input/output) | $0.95 / $4.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 43.7 (Supported · #57/124)
- Soofi S 30B-A3B public-lane score: Coming soon

| Benchmark | Kimi K2.6 | Soofi S 30B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 66.7% | Coming soon | Coming soon |
| BrowseComp | 83.2% | Coming soon | Coming soon |
| OSWorld-Verified | 73.1% | Coming soon | Coming soon |
| Toolathlon | 50% | Coming soon | Coming soon |
| MCP Atlas | 55.9% | Coming soon | Coming soon |
| Claw-Eval | 62.3% | Coming soon | Coming soon |
| DeepSearchQA | 92.5% | Coming soon | Coming soon |
| WideResearch | 80.8% | Coming soon | Coming soon |
| Gert Labs | 56.82% | Coming soon | Coming soon |
| ResearchClawBench | 18.0% | 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
- Kimi K2.6 public-lane score: 43.6 (Supported · #55/149)
- Soofi S 30B-A3B public-lane score: Coming soon

| Benchmark | Kimi K2.6 | Soofi S 30B-A3B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 80.2% | Coming soon | Coming soon |
| LiveCodeBench v6 | 89.6% | Coming soon | Coming soon |
| SWE-bench Pro | 58.6% | Coming soon | Coming soon |
| SWE Multilingual | 76.7% | Coming soon | Coming soon |
| SciCode | 52.2% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 66.7% | Coming soon | Coming soon |
| Vibe Code Bench | 37.89% | Coming soon | Coming soon |
| cursorBench31 | 47.6% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 86.8% | Coming soon | Coming soon |
| SWE-bench (Vals) | 76.2% | Coming soon | Coming soon |
| HumanEval | Coming soon | 73.8% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: Coming soon
- Soofi S 30B-A3B public-lane score: Coming soon

| Benchmark | Kimi K2.6 | Soofi S 30B-A3B | Winner |
|-----------|-----------|-----------|--------|
| BBH | Coming soon | 78.8% | Coming soon |
| DROP | Coming soon | 66.5% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 73.8 (#27/54)
- Soofi S 30B-A3B public-lane score: Coming soon

| Benchmark | Kimi K2.6 | Soofi S 30B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | 79.4% | Coming soon | Coming soon |
| MMMU-Pro w/ Python | 80.1% | Coming soon | Coming soon |
| CharXiv | 80.4% | Coming soon | Coming soon |
| MathVision | 87.4% | Coming soon | Coming soon |
| V* | 96.9% | Coming soon | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 60 (Supported · #48/181)
- Soofi S 30B-A3B public-lane score: Coming soon

| Benchmark | Kimi K2.6 | Soofi S 30B-A3B | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 90.5% | 43.4% | Kimi K2.6 |
| GPQA-D | 90.5% | 43.4% | Kimi K2.6 |
| HLE | 34.7% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 89.1% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 87.6% | Coming soon | Coming soon |
| MMLU-Pro | Coming soon | 51.4% | Coming soon |
| AGIEval | Coming soon | 66.9% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Kimi K2.6 public-lane score: 76.8 (#4/12)
- Soofi S 30B-A3B public-lane score: Coming soon

| Benchmark | Kimi K2.6 | Soofi S 30B-A3B | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | 96.4% | Coming soon | Coming soon |
| HMMT Feb 2026 | 92.7% | Coming soon | Coming soon |
| MMAnswerBench | 86.0% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 57.193% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 25.641% | Coming soon | Coming soon |
| GSM8K | Coming soon | 86.1% | Coming soon |

## FAQ

### Is there enough evidence to pick between Kimi K2.6 and Soofi S 30B-A3B?

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

- [Kimi K2.6 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-kimi-2-6)
- [Soofi S 30B-A3B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-soofi-s-30b-a3b)
- [Kimi K2.6 vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-kimi-2-6)
- [Soofi S 30B-A3B vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-soofi-s-30b-a3b)

## Explore More

- [Kimi K2.6 profile](/models/kimi-2-6)
- [Soofi S 30B-A3B profile](/models/soofi-s-30b-a3b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)