# Claude Haiku 4.5 vs MiniMax M2.7

> Side-by-side benchmark comparison for Claude Haiku 4.5 and MiniMax M2.7 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-haiku-4-5-vs-minimax-m2-7
- Last updated: September 15, 2026

- Shared sourced benchmarks: 5
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Pick MiniMax M2.7 if you want the stronger benchmark profile. Claude Haiku 4.5 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- MiniMax M2.7 leads overall 55.14 to 52.91.
- The clearest category separation is in coding, where the averages are 27.4 for Claude Haiku 4.5 and 48.6 for MiniMax M2.7.
- The biggest single benchmark swing is LiveCodeBench (Vals) in Coding, with scores of 41.2% and 79.9%.
- MiniMax M2.7 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Claude Haiku 4.5 | MiniMax M2.7 |
|----------|----------|----------|
| Creator | Anthropic | MiniMax |
| Type | Proprietary | Open Weight |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | 200K | 200K |
| Overall Score | 52.91 | 55.14 |
| Benchmarks Covered | 10 | 23 |
| Pricing (input/output) | $1.00 / $5.00 | $0.30 / $1.20 |

## Category Breakdown

### Agentic

- Winner: Coming soon
- Claude Haiku 4.5 public-lane score: 27 (Supported · #143/153)
- MiniMax M2.7 public-lane score: 41.1 (Estimated · #110/153)

| Benchmark | Claude Haiku 4.5 | MiniMax M2.7 | Winner |
|-----------|-----------|-----------|--------|
| JobBench | 16.0% | Coming soon | Coming soon |
| Terminal-Bench 2.1 (Vals) | 43.8% | 48.7% | MiniMax M2.7 |
| Terminal-Bench 2.0 | Coming soon | 57% | Coming soon |
| Toolathlon | Coming soon | 46.3% | Coming soon |
| MLE-Bench Lite | Coming soon | 66.6% | Coming soon |
| MM-ClawBench | Coming soon | 62.7% | Coming soon |
| Claw-Eval | Coming soon | 48.7% | Coming soon |
| Gert Labs | Coming soon | 40.40% | Coming soon |

### Coding

- Winner: Coming soon
- Claude Haiku 4.5 public-lane score: 27.4 (Supported · #144/152)
- MiniMax M2.7 public-lane score: 48.6 (Estimated · #68/152)

| Benchmark | Claude Haiku 4.5 | MiniMax M2.7 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 73.3% | Coming soon | Coming soon |
| VulcanBench v3 | 76.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 41.2% | 79.9% | MiniMax M2.7 |
| SWE-bench (Vals) | 66.6% | 73.8% | MiniMax M2.7 |
| SWE-bench Verified* | Coming soon | 75.4% | Coming soon |
| SWE-bench Pro | Coming soon | 56.2% | Coming soon |
| SWE-Rebench | Coming soon | 51.9% | Coming soon |
| SWE Multilingual | Coming soon | 76.5% | Coming soon |
| Multi-SWE Bench | Coming soon | 52.7% | Coming soon |
| VIBE-Pro | Coming soon | 55.6% | Coming soon |
| NL2Repo | Coming soon | 39.8% | Coming soon |
| Vibe Code Bench | Coming soon | 27.04% | Coming soon |
| React Native Evals | Coming soon | 71.4% | Coming soon |

### Reasoning

- Winner: Coming soon
- Claude Haiku 4.5 public-lane score: Coming soon
- MiniMax M2.7 public-lane score: 74.8 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Coming soon
- Claude Haiku 4.5 public-lane score: 44.3 (Estimated · #115/183)
- MiniMax M2.7 public-lane score: 48.7 (Supported · #90/183)

| Benchmark | Claude Haiku 4.5 | MiniMax M2.7 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 72.2% | 86.6% | MiniMax M2.7 |
| MMLU-Pro (Vals) | 78.7% | 80.4% | MiniMax M2.7 |
| GPQA-D | Coming soon | 87.0% | Coming soon |
| MMLU-Pro (Arcee) | Coming soon | 80.8% | Coming soon |

### Instruction Following

- Winner: Coming soon
- Claude Haiku 4.5 public-lane score: Coming soon
- MiniMax M2.7 public-lane score: 93 (#10/123)

### Mathematics

- Winner: Coming soon
- Claude Haiku 4.5 public-lane score: 28.9 (Unranked · 2 rankable rows)
- MiniMax M2.7 public-lane score: Coming soon

| Benchmark | Claude Haiku 4.5 | MiniMax M2.7 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 5.903% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 2.083% | Coming soon | Coming soon |
| AIME25 (Arcee) | Coming soon | 80.0% | Coming soon |

## FAQ

### Which is better overall, Claude Haiku 4.5 or MiniMax M2.7?

MiniMax M2.7 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Haiku 4.5 and MiniMax M2.7?

The widest category gap is in coding, where the averages are 27.4 for Claude Haiku 4.5 and 48.6 for MiniMax M2.7.

### How many benchmarks does Claude Haiku 4.5 cover on BenchLM?

Claude Haiku 4.5 currently has 10 sourced benchmark scores on BenchLM.

### How many benchmarks does MiniMax M2.7 cover on BenchLM?

MiniMax M2.7 currently has 23 sourced benchmark scores on BenchLM.

## Related Comparisons

- [Claude Haiku 4.5 vs Claude Haiku 4.5 Thinking](/compare/claude-haiku-4-5-vs-claude-haiku-4-5-thinking)
- [MiniMax M2.7 vs Claude Haiku 4.5 Thinking](/compare/claude-haiku-4-5-thinking-vs-minimax-m2-7)
- [Claude Haiku 4.5 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-claude-haiku-4-5)
- [MiniMax M2.7 vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-minimax-m2-7)

## Explore More

- [Claude Haiku 4.5 profile](/models/claude-haiku-4-5)
- [MiniMax M2.7 profile](/models/minimax-m2-7)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)