# Claude Sonnet 4.6 vs MiniMax M3

> Side-by-side benchmark comparison for Claude Sonnet 4.6 and MiniMax M3 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-sonnet-4-6-vs-minimax-m3
- Last updated: October 15, 2026

- Shared sourced benchmarks: 9
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Claude Sonnet 4.6 if you want the stronger benchmark profile. MiniMax M3 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Claude Sonnet 4.6 leads overall 55.85 to 54.94.
- The clearest category separation is in instruction following, where the averages are 48 for Claude Sonnet 4.6 and 93.8 for MiniMax M3.
- The biggest single benchmark swing is GPQA Diamond (Vals) in Knowledge, with scores of 85.6% and 92.7%.
- MiniMax M3 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- MiniMax M3 also has the larger context window at 1M.

## Model Snapshot

| Property | Claude Sonnet 4.6 | MiniMax M3 |
|----------|----------|----------|
| Creator | Anthropic | MiniMax |
| Type | Proprietary | Open Weight |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | 200K | 1M |
| Overall Score | 55.85 | 54.94 |
| Benchmarks Covered | 27 | 27 |
| Pricing (input/output) | $3.00 / $15.00 | $0.30 / $1.20 |

## Category Breakdown

### Agentic

- Winner: Claude Sonnet 4.6
- Claude Sonnet 4.6 public-lane score: 46.4 (Supported · #54/126)
- MiniMax M3 public-lane score: 39.4 (Supported · #67/126)

| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 59.1% | Coming soon | Coming soon |
| OSWorld-Verified | 72.1% | 70.1% | Claude Sonnet 4.6 |
| Claw-Eval | 67.8% | 74.5% | MiniMax M3 |
| CyberGym | 65.2% | Coming soon | Coming soon |
| Gert Labs | 62.92% | Coming soon | Coming soon |
| OSWorld 2.0 | 8.3% | 4.6% | Claude Sonnet 4.6 |
| JobBench | 36.9% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 57.3% | 53.6% | Claude Sonnet 4.6 |
| ApprenticeBench | 2% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 66.0% | Coming soon |
| BrowseComp | Coming soon | 83.5% | Coming soon |
| MCP Atlas | Coming soon | 74.2% | Coming soon |
| BankerToolBench | Coming soon | 76.1% | Coming soon |
| ResearchClawBench | Coming soon | 19.8% | Coming soon |

### Coding

- Winner: Claude Sonnet 4.6
- Claude Sonnet 4.6 public-lane score: 44.8 (Supported · #53/149)
- MiniMax M3 public-lane score: 36.5 (Supported · #73/149)

| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 79.6% | 80.5% | MiniMax M3 |
| SWE-Rebench | 60.7% | Coming soon | Coming soon |
| React Native Evals | 80.6% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 59.1% | Coming soon | Coming soon |
| Vibe Code Bench | 51.48% | Coming soon | Coming soon |
| cursorBench31 | 48.8% | Coming soon | Coming soon |
| FrontierCode 1.1 Main | 24.3% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 82.1% | 82.2% | MiniMax M3 |
| SWE-bench (Vals) | 77.4% | 75.0% | Claude Sonnet 4.6 |
| SWE-bench Pro | Coming soon | 59% | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 66.0% | Coming soon |
| NL2Repo | Coming soon | 42.1% | Coming soon |
| VIBE V2 | Coming soon | 50.1% | Coming soon |
| SVG-Bench | Coming soon | 63.7% | Coming soon |
| KernelBench Hard | Coming soon | 28.8% | Coming soon |
| OpenHarmony Bench | Coming soon | 48.4% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: 62.8 (Unranked · 4 rankable rows)
- MiniMax M3 public-lane score: 82.9 (#5/29)

| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 58.3% | Coming soon | Coming soon |
| ARC-AGI-1 | 86.00% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Directional only
- Claude Sonnet 4.6 public-lane score: 58.7 (#45/54)
- MiniMax M3 public-lane score: 61.5 (#43/54)

| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| CharXiv | 77.4% | Coming soon | Coming soon |
| OfficeQA Pro | Coming soon | 45.1% | Coming soon |
| OmniDocBench 1.5 | Coming soon | 91.6% | Coming soon |
| MMMU-Pro | Coming soon | 78.1% | Coming soon |
| VideoMMMU | Coming soon | 84.6% | Coming soon |
| Video-MME (with subtitle) | Coming soon | 85.4% | Coming soon |

### Knowledge

- Winner: Claude Sonnet 4.6
- Claude Sonnet 4.6 public-lane score: 55.2 (Supported · #57/182)
- MiniMax M3 public-lane score: 49.6 (Supported · #81/182)

| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 89.9% | Coming soon | Coming soon |
| SuperGPQA | 95% | Coming soon | Coming soon |
| MMLU-Pro | 79.2% | Coming soon | Coming soon |
| HLE | 49% | Coming soon | Coming soon |
| GPQA Diamond (Vals) | 85.6% | 92.7% | MiniMax M3 |
| MMLU-Pro (Vals) | 87.3% | 84.2% | Claude Sonnet 4.6 |

### Instruction Following

- Winner: Directional only
- Claude Sonnet 4.6 public-lane score: 48 (#97/146)
- MiniMax M3 public-lane score: 93.8 (#5/146)

### Mathematics

- Winner: Not comparable
- Claude Sonnet 4.6 public-lane score: Coming soon
- MiniMax M3 public-lane score: Coming soon

| Benchmark | Claude Sonnet 4.6 | MiniMax M3 | Winner |
|-----------|-----------|-----------|--------|
| USAMO 2026 | Coming soon | 85.7% | Coming soon |

## FAQ

### Which is better overall, Claude Sonnet 4.6 or MiniMax M3?

Claude Sonnet 4.6 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Sonnet 4.6 and MiniMax M3?

The widest category gap is in instruction following, where the averages are 48 for Claude Sonnet 4.6 and 93.8 for MiniMax M3.

### How many benchmarks does Claude Sonnet 4.6 cover on BenchLM?

Claude Sonnet 4.6 currently has 27 sourced benchmark scores on BenchLM.

### How many benchmarks does MiniMax M3 cover on BenchLM?

MiniMax M3 currently has 27 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Sonnet 4.6 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-claude-sonnet-4-6)
- [MiniMax M3 vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-minimax-m3)
- [Claude Sonnet 4.6 vs GPT-6.1 Sol](/compare/claude-sonnet-4-6-vs-gpt-6-1-sol)
- [MiniMax M3 vs GPT-6.1 Sol](/compare/gpt-6-1-sol-vs-minimax-m3)

## Explore More

- [Claude Sonnet 4.6 profile](/models/claude-sonnet-4-6)
- [MiniMax M3 profile](/models/minimax-m3)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)