# Claude Haiku 4.5 vs Claude Sonnet 4.5

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

- Canonical page: https://benchlm.ai/compare/claude-haiku-4-5-vs-claude-sonnet-4-5
- Last updated: September 29, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Pick Claude Sonnet 4.5 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

- Claude Sonnet 4.5 leads overall 47.85 to 42.47.
- The clearest category separation is in agentic, where the averages are 22 for Claude Haiku 4.5 and 34.6 for Claude Sonnet 4.5.
- The biggest single benchmark swing is JobBench in Agentic, with scores of 16.0% and 27.7%.
- Claude Haiku 4.5 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 | Claude Sonnet 4.5 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Non-Reasoning |
| Context | 200K | 200K |
| Overall Score | 42.47 | 47.85 |
| Benchmarks Covered | 10 | 11 |
| Pricing (input/output) | $1.00 / $5.00 | $3.00 / $15.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Claude Haiku 4.5 public-lane score: 22 (Supported · #96/117)
- Claude Sonnet 4.5 public-lane score: 34.6 (Estimated · #67/117)

| Benchmark | Claude Haiku 4.5 | Claude Sonnet 4.5 | Winner |
|-----------|-----------|-----------|--------|
| JobBench | 16.0% | 27.7% | Claude Sonnet 4.5 |
| Terminal-Bench 2.1 (Vals) | 43.8% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 50% | Coming soon |
| OSWorld-Verified | Coming soon | 61.4% | Coming soon |
| VITA-Bench | Coming soon | 17.0% | Coming soon |
| Gert Labs | Coming soon | 48.51% | Coming soon |

### Coding

- Winner: Not comparable
- Claude Haiku 4.5 public-lane score: 19.6 (Supported · #124/143)
- Claude Sonnet 4.5 public-lane score: Coming soon

| Benchmark | Claude Haiku 4.5 | Claude Sonnet 4.5 | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 73.3% | 77.2% | Claude Sonnet 4.5 |
| VulcanBench v3 | 76.2% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 41.2% | Coming soon | Coming soon |
| SWE-bench (Vals) | 66.6% | Coming soon | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Haiku 4.5 public-lane score: Coming soon
- Claude Sonnet 4.5 public-lane score: 19.2 (Unranked · 1 rankable row)

| Benchmark | Claude Haiku 4.5 | Claude Sonnet 4.5 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | Coming soon | 13.6% | Coming soon |

### Knowledge

- Winner: Not comparable
- Claude Haiku 4.5 public-lane score: 34.8 (Estimated · #119/169)
- Claude Sonnet 4.5 public-lane score: Coming soon

| Benchmark | Claude Haiku 4.5 | Claude Sonnet 4.5 | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 72.2% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 78.7% | Coming soon | Coming soon |
| GPQA | Coming soon | 83.4% | Coming soon |

### Mathematics

- Winner: Not comparable
- Claude Haiku 4.5 public-lane score: 28.8 (Unranked · 2 rankable rows)
- Claude Sonnet 4.5 public-lane score: 34.6 (Unranked · 2 rankable rows)

| Benchmark | Claude Haiku 4.5 | Claude Sonnet 4.5 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 5.903% | 13.495% | Claude Sonnet 4.5 |
| FrontierMath v2 (Tier 4) | 2.083% | 4.167% | Claude Sonnet 4.5 |
| AIME 2025 | Coming soon | 87% | Coming soon |

## FAQ

### Which is better overall, Claude Haiku 4.5 or Claude Sonnet 4.5?

Claude Sonnet 4.5 is ahead overall on BenchLM right now.

### Where is the biggest gap between Claude Haiku 4.5 and Claude Sonnet 4.5?

The widest category gap is in agentic, where the averages are 22 for Claude Haiku 4.5 and 34.6 for Claude Sonnet 4.5.

### 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 Claude Sonnet 4.5 cover on BenchLM?

Claude Sonnet 4.5 currently has 11 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)
- [Claude Sonnet 4.5 vs Claude Haiku 4.5 Thinking](/compare/claude-haiku-4-5-thinking-vs-claude-sonnet-4-5)
- [Claude Haiku 4.5 vs Claude Sonnet 4.5 Thinking](/compare/claude-haiku-4-5-vs-claude-sonnet-4-5-thinking)
- [Claude Sonnet 4.5 vs Claude Sonnet 4.5 Thinking](/compare/claude-sonnet-4-5-vs-claude-sonnet-4-5-thinking)

## Explore More

- [Claude Haiku 4.5 profile](/models/claude-haiku-4-5)
- [Claude Sonnet 4.5 profile](/models/claude-sonnet-4-5)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)