# Claude Mythos 5.2 vs Claude Opus 5.5

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

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

- Shared sourced benchmarks: 14
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick Claude Opus 5.5 if you want the stronger benchmark profile. Claude Mythos 5.2 only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- Claude Opus 5.5 leads overall 85.82 to 0.
- The biggest single benchmark swing is Binary Exploitation Benchmark in Agentic, with scores of 148 and 112.
- Claude Opus 5.5 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.

## Model Snapshot

| Property | Claude Mythos 5.2 | Claude Opus 5.5 |
|----------|----------|----------|
| Creator | Anthropic | Anthropic |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 1M | 1M |
| Overall Score | null | 85.82 |
| Benchmarks Covered | 14 | 82 |
| Pricing (input/output) | $8.00 / $40.00 | $4.00 / $20.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- Claude Mythos 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: 89.3 (Supported · #2/132)

| Benchmark | Claude Mythos 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 4.0 | 70.50% | 66.40% | Claude Mythos 5.2 |
| Terminal-Bench-Science 0.1 | 75.3% | 58.7% | Claude Mythos 5.2 |
| CVE Rediscovery | 89.6% | 81.3% | Claude Mythos 5.2 |
| ExploitGym | 38.1% | 33.3% | Claude Mythos 5.2 |
| Binary Exploitation Benchmark | 148 | 112 | Claude Mythos 5.2 |
| Terminal-Bench 4.1 | Coming soon | 65.80% | Coming soon |
| AutomationBench | Coming soon | 40.0% | Coming soon |
| HLE w/ tools | Coming soon | 67.7% | Coming soon |
| OSWorld 2.0 | Coming soon | 48.7% | Coming soon |
| LAB all-pass (Harvey held-out) | Coming soon | 8.3% | Coming soon |
| LAB criterion-pass (Harvey held-out) | Coming soon | 91.2% | Coming soon |
| Toolathlon-Verified | Coming soon | 77.8% | Coming soon |
| Toolathlon Verified Pass@3 | Coming soon | 82.4% | Coming soon |
| Toolathlon Verified Pass³ | Coming soon | 72.2% | Coming soon |
| Toolathlon Verified avg. turns | Coming soon | 26.9 turns | Coming soon |
| CWE-bench v1 | Coming soon | 67.0% | Coming soon |
| Hermes Index | Coming soon | 63.3% | Coming soon |
| Hermes Bench | Coming soon | 76.7% | Coming soon |
| MazeBench | Coming soon | 13% | Coming soon |
| OSWorld 2.1 | Coming soon | 81.8% | Coming soon |
| OSWorld 2.1 Offline | Coming soon | 87.2% | Coming soon |
| WANDR | Coming soon | 72.3% | Coming soon |
| RoboDojo Sim | Coming soon | 39.4% | Coming soon |
| Remote Labor Index | Coming soon | 21.3% | Coming soon |
| DRACO | Coming soon | 87.4% | Coming soon |
| CWE-bench | Coming soon | 67.1% | Coming soon |

### Coding

- Winner: Not comparable
- Claude Mythos 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: 82.4 (Supported · #2/158)

| Benchmark | Claude Mythos 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| ScarfBench | Coming soon | 70.5% | Coming soon |
| FrontierCode 1.1 Main | Coming soon | 54.4% | Coming soon |
| CursorBench 4.0 | Coming soon | 57.8% | Coming soon |
| SWE-bench Pro | Coming soon | 89.9% | Coming soon |
| SWE Multilingual | Coming soon | 93.9% | Coming soon |
| SWE Multimodal | Coming soon | 61.4% | Coming soon |
| DeepSWE | Coming soon | 74.2% | Coming soon |
| FrontierCode 1.1 Extended | Coming soon | 63.6% | Coming soon |
| FrontierSWE v2 | Coming soon | 62.3% | Coming soon |
| ProgramBench | Coming soon | 91.2% | Coming soon |
| PostTrainBench v1.1 | Coming soon | 49.3% | Coming soon |
| Bug Hunt Bench | Coming soon | 41.7 fixes | Coming soon |
| FrontierCode 2.0 | Coming soon | 45.5% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Mythos 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: 80 (Supported · #4/157)

| Benchmark | Claude Mythos 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| STEMBench | Coming soon | 2.62 | Coming soon |
| ARC-AGI-1 | Coming soon | 97.50% | Coming soon |
| ARC-AGI-2 | Coming soon | 91.7% | Coming soon |
| GraphWalks BFS 256K–1M | Coming soon | 66.8% | Coming soon |
| STEM Professor Bench | Coming soon | 53.7% | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Claude Mythos 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: 84.4 (Supported · #2/67)

| Benchmark | Claude Mythos 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Biomedical image analysis | 80.7% | 71.4% | Claude Mythos 5.2 |
| ExtractBench Pro | Coming soon | 51% | Coming soon |
| ExtractBench (LlamaIndex) | Coming soon | 86.06% | Coming soon |
| ParseBench | Coming soon | 78.80% | Coming soon |
| Chartography (tools) | Coming soon | 89.0% | Coming soon |
| Chartography (no tools) | Coming soon | 64.4% | Coming soon |
| BenchCAD Vision2Code (no tools) | Coming soon | 0.730 | Coming soon |
| BenchCAD Vision2Code (tools) | Coming soon | 0.962 | Coming soon |
| OfficeQA | Coming soon | 78.9% | Coming soon |
| OfficeQA Pro | Coming soon | 67.7% | Coming soon |
| BenchCAD 2.1 | Coming soon | 49.0% | Coming soon |
| BenchCAD 2.1 (tools) | Coming soon | 65.3% | Coming soon |

### Knowledge

- Winner: Not comparable
- Claude Mythos 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: 88.1 (Supported · #2/179)

| Benchmark | Claude Mythos 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| De novo protein-binder design | 85.1% | 82.6% | Claude Mythos 5.2 |
| Protein Design | 64.6% | 60.2% | Claude Mythos 5.2 |
| SingleCellBench | 65.6% | 61.2% | Claude Mythos 5.2 |
| Protocols (troubleshooting) | 77.1% | 73.7% | Claude Mythos 5.2 |
| Protein Domain ID | 91.8% | 73.6% | Claude Mythos 5.2 |
| Protein Mutation Attribution | 51.5% | 49.5% | Claude Mythos 5.2 |
| Morphology-to-molecule matching | 35.2% | 34.0% | Claude Mythos 5.2 |
| Medicinal chemistry | 69.0% | 63.5% | Claude Mythos 5.2 |
| HLE w/o tools | Coming soon | 64.4% | Coming soon |
| HealthBench (raw) | Coming soon | 68.1% | Coming soon |
| HealthBench (length-adjusted) | Coming soon | 60.6% | Coming soon |
| HealthBench Professional | Coming soon | 65.6% | Coming soon |
| HealthBench Professional (raw) | Coming soon | 77.1% | Coming soon |
| BioMysteryBench (human-solvable) | Coming soon | 89.3% | Coming soon |
| BioMysteryBench (human-difficult) | Coming soon | 50.0% | Coming soon |
| SpatialBench Verified | Coming soon | 72.0% | Coming soon |
| Protein Design library ranking | Coming soon | 56.0% | Coming soon |
| Protocols (understanding) | Coming soon | 69.0% | Coming soon |
| PhysicianBench | Coming soon | 68.4% | Coming soon |

### Multilingual

- Winner: Not comparable
- Claude Mythos 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: Coming soon

| Benchmark | Claude Mythos 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| GMMLU | Coming soon | 94.3% | Coming soon |
| MILU | Coming soon | 93.1% | Coming soon |

### Instruction Following

- Winner: Not comparable
- Claude Mythos 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: Coming soon

| Benchmark | Claude Mythos 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| Gray Swan IPI (15 attempts) | Coming soon | 1.0% | Coming soon |

### Mathematics

- Winner: Not comparable
- Claude Mythos 5.2 public-lane score: Coming soon
- Claude Opus 5.5 public-lane score: 93.8 (Unranked · 4 rankable rows)

| Benchmark | Claude Mythos 5.2 | Claude Opus 5.5 | Winner |
|-----------|-----------|-----------|--------|
| ArXivMath Aug. 2026 (no tools) | Coming soon | 91.2% | Coming soon |
| ArXivMath Aug. 2026 (tools) | Coming soon | 96.9% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 91.228% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 95.000% | Coming soon |

## FAQ

### Which is better overall, Claude Mythos 5.2 or Claude Opus 5.5?

Claude Opus 5.5 is ahead overall on BenchLM right now.

### How many benchmarks does Claude Mythos 5.2 cover on BenchLM?

Claude Mythos 5.2 currently has 14 sourced benchmark scores on BenchLM.

### How many benchmarks does Claude Opus 5.5 cover on BenchLM?

Claude Opus 5.5 currently has 82 sourced benchmark scores on BenchLM.

## Related Comparisons

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

## Explore More

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