# Claude Haiku 5.5 vs Claude Mythos 5.2

> Side-by-side benchmark comparison for Claude Haiku 5.5 and Claude Mythos 5.2 across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-haiku-5-5-vs-claude-mythos-5-2
- Last updated: November 10, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: Claude Haiku 5.5 and Claude Mythos 5.2 share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Claude Haiku 5.5 has the lower published output-token price.

## Model Snapshot

| Property | Claude Haiku 5.5 | Claude Mythos 5.2 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Independent public score (not head-to-head) | 66.17 | null |
| Benchmarks Covered | 22 | 14 |
| Pricing (input/output) | $0.10 / $0.50 | $8.00 / $40.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- Claude Haiku 5.5 public-lane score: 60.7 (Supported · #25/132)
- Claude Mythos 5.2 public-lane score: Coming soon

| Benchmark | Claude Haiku 5.5 | Claude Mythos 5.2 | Winner |
|-----------|-----------|-----------|--------|
| Agents' Last Exam (Linux) | 57.0% | Coming soon | Coming soon |
| Terminal-Bench 4.0 | 39.20% | 70.50% | Claude Mythos 5.2 |
| HLE w/ tools | 57.4% | Coming soon | Coming soon |
| MazeBench | 1% | Coming soon | Coming soon |
| Hermes Index | 37.0% | Coming soon | Coming soon |
| Hermes Bench | 71.0% | Coming soon | Coming soon |
| OSWorld 2.1 Offline | 72.4% | Coming soon | Coming soon |
| Terminal-Bench-Science 0.1 | Coming soon | 75.3% | Coming soon |
| CVE Rediscovery | Coming soon | 89.6% | Coming soon |
| ExploitGym | Coming soon | 38.1% | Coming soon |
| Binary Exploitation Benchmark | Coming soon | 148 | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- Claude Haiku 5.5 public-lane score: 51.7 (Supported · #42/158)
- Claude Mythos 5.2 public-lane score: Coming soon

| Benchmark | Claude Haiku 5.5 | Claude Mythos 5.2 | Winner |
|-----------|-----------|-----------|--------|
| FrontierCode 1.1 Main | 46.4% | Coming soon | Coming soon |
| Bug Hunt Bench | 21.5 fixes | Coming soon | Coming soon |
| FrontierSWE v2 | 43.8% | Coming soon | Coming soon |
| FrontierCode 2.0 | 27.7% | Coming soon | Coming soon |
| CursorBench 4.0 | 48.4% | Coming soon | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- Claude Haiku 5.5 public-lane score: 58.1 (Supported · #38/158)
- Claude Mythos 5.2 public-lane score: Coming soon

| Benchmark | Claude Haiku 5.5 | Claude Mythos 5.2 | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-1 | 89.00% | Coming soon | Coming soon |
| ARC-AGI-2 | 61.3% | Coming soon | Coming soon |
| ARC-AGI-3 | 0.5% | Coming soon | Coming soon |
| ARC-AGI-3 Provider Adapter | 2.82% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- Claude Haiku 5.5 public-lane score: 60.7 (Supported · #35/67)
- Claude Mythos 5.2 public-lane score: Coming soon

| Benchmark | Claude Haiku 5.5 | Claude Mythos 5.2 | Winner |
|-----------|-----------|-----------|--------|
| PerceptionBench (tools) | 78.6% | Coming soon | Coming soon |
| ParseBench | 56.02% | Coming soon | Coming soon |
| Chartography (no tools) | 46.4% | Coming soon | Coming soon |
| Biomedical image analysis | Coming soon | 80.7% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- Claude Haiku 5.5 public-lane score: 63.4 (Supported · #38/179)
- Claude Mythos 5.2 public-lane score: Coming soon

| Benchmark | Claude Haiku 5.5 | Claude Mythos 5.2 | Winner |
|-----------|-----------|-----------|--------|
| HLE w/o tools | 45.9% | Coming soon | Coming soon |
| De novo protein-binder design | Coming soon | 85.1% | Coming soon |
| Protein Design | Coming soon | 64.6% | Coming soon |
| SingleCellBench | Coming soon | 65.6% | Coming soon |
| Protocols (troubleshooting) | Coming soon | 77.1% | Coming soon |
| Protein Domain ID | Coming soon | 91.8% | Coming soon |
| Protein Mutation Attribution | Coming soon | 51.5% | Coming soon |
| Morphology-to-molecule matching | Coming soon | 35.2% | Coming soon |
| Medicinal chemistry | Coming soon | 69.0% | Coming soon |

### Mathematics

- Winner: Insufficient shared evidence
- Claude Haiku 5.5 public-lane score: 74.3 (Unranked · 2 rankable rows)
- Claude Mythos 5.2 public-lane score: Coming soon

| Benchmark | Claude Haiku 5.5 | Claude Mythos 5.2 | Winner |
|-----------|-----------|-----------|--------|
| FrontierMath v2 (Tiers 1-3) | 75.088% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 46.341% | Coming soon | Coming soon |

## FAQ

### Is there enough evidence to pick between Claude Haiku 5.5 and Claude Mythos 5.2?

Not yet. The models share only 1 sourced benchmark row, 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

- [Claude Haiku 5.5 vs Claude Mythos 5](/compare/claude-haiku-5-5-vs-claude-mythos-5)
- [Claude Mythos 5.2 vs Claude Mythos 5](/compare/claude-mythos-5-vs-claude-mythos-5-2)
- [Claude Haiku 5.5 vs Claude Mythos 5.1](/compare/claude-haiku-5-5-vs-claude-mythos-5-1)
- [Claude Mythos 5.2 vs Claude Mythos 5.1](/compare/claude-mythos-5-1-vs-claude-mythos-5-2)

## Explore More

- [Claude Haiku 5.5 profile](/models/claude-haiku-5-5)
- [Claude Mythos 5.2 profile](/models/claude-mythos-5-2)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)