- SWE-bench Verified 93.9
- SWE-bench Pro 77.8
- SWE-bench Multilingual 87.3
- SWE-bench Multimodal (internal implementation) 59
- Terminal-Bench 2.0 (Terminus-2) 82
- GPQA Diamond 94.5
- MMMLU 92.7
- USAMO 2026 97.6
- GraphWalks BFS 256K-1M 80
- HLE (with tools) 64.7
- CharXiv Reasoning (with tools) 93.2
- OSWorld 79.6
- BrowseComp (Glasswing page) 86.9
Claude Mythos Preview
Claude Mythos Preview ranks first on 14 of the 46 benchmarks it has scores on.
55
Benchmarks with a score
14
Ranked first, out of five or more models
27
In the top three
Anthropic Apr 2026
Claude Mythos Preview
Closed weights Flagship
No Epoch Capabilities Index score yet
- AA-Omniscience 70.8% #1 /17
- SWE-bench Multimodal 59% #3 /10
- Virology Capabilities Test (VCT) 57.4% #10 /28
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MMMLU | 92.7% | #1 of 62 | Model card | |
| Humanity's Last Exam | 64.7% | #4 of 147 | Model card | |
| AA-Omniscience | 70.8% | #1 of 17 | Model card | |
| ECLeKTic | 56.3% | #1 of 10 | Model card | |
| 100Q-Hard (Anthropic) | 60.1% | #1 of 7 | Model card | |
| SimpleQA Verified | 70.7% | #4 of 22 | Model card | |
| GraphWalks | 80% | #10 of 21 | Model card | |
| False-premise questions (Anthropic) | 80% | #5 of 6 | Model card |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| GPQA Diamond | 94.5% | #2 of 284 | Model card | |
| USAMO 2026 | 97.6% | #1 of 6 | Model card |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SWE-bench Verified | 93.9% | #3 of 150 | Model card | |
| METR Time Horizon | 17.4 h | #1 of 39 | Epoch AI | |
| METR Time Horizon 1.1 | 17.4 h | #1 of 26 | Official leaderboard | |
| SWE-Bench Pro | 77.8% | #6 of 77 | Model card | |
| SWE-bench Multilingual | 87.3% | #6 of 70 | Model card | |
| Time series forecasting task (Anthropic) | 4.55 | #1 of 9 | Model card | |
| Internal AI research evaluation suite 2 | 0.65 | #1 of 6 | Model card | |
| Quadruped reinforcement learning task (Anthropic) | 30.9 | #2 of 8 | Model card | |
| SWE-bench Multimodal | 59% | #3 of 10 | Model card | |
| Internal model use survey (Anthropic) | 5.60% | #2 of 5 | Model card | |
| Novel compiler task (Anthropic) | 77.2% | #2 of 4 | Model card | |
| Key insight rediscovery on an unpublished ML task (external testing) | 80% | #1 of 1 | Model card |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Terminal-Bench 2.0 | 82% | #2 of 61 | Model card | |
| BrowseComp | 86.9% | #14 of 77 | Model card | |
| ScreenSpot-Pro | 79.5% | #7 of 25 | Model card | |
| OSWorld-Verified | 79.6% | #11 of 37 | Model card |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| CharXiv | 93.2% | #3 of 67 | Model card |
Safety and security
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Recognition of model-written user turns (Anthropic) | 0.35 | #1 of 1 | Model card |
Its launch post
The benchmarks the lab chose to headline, with the scores it gave.
Its system card
Every result in the longer documents the lab published with it. 61 of them aren't in the launch post.
System Card: Claude Mythos Preview 7 Apr 2026
Capabilities
- SWE-bench Verified 93.9
- SWE-Bench Pro 77.8
- SWE-bench Multilingual 87.3
- SWE-bench Multimodal 59
- Terminal-Bench 2.0 82
- GPQA Diamond 94.5
- MMMLU 92.7
- USAMO 2026 97.6
- GraphWalks
- Humanity's Last Exam 56.8
- BrowseComp 86.9
- LAB-Bench FigQA 79.7
- ScreenSpot-Pro 79.5
- CharXiv 86.1
- OSWorld-Verified 79.6
Hallucination
Safety
- Single-turn harmful request evaluations (Anthropic) 97.8
- Single-turn benign request evaluations (Anthropic) 0.06
- Higher-difficulty harmful request evaluations (Anthropic) 99.1
- Higher-difficulty benign request evaluations (Anthropic) 0.02
- Multi-turn testing (Anthropic)
- Child safety evaluations (Anthropic)
- Suicide and self-harm evaluations (Anthropic)
- Disordered eating evaluations (Anthropic)
- Malicious use of Claude Code (Anthropic) 96.7
- Malicious computer use (Anthropic) 93.8
- Malicious agentic influence campaigns (Anthropic)
Robustness
Alignment
- Impossible tasks (Anthropic) 37.5
- Agentic code behavior scores (Anthropic)
- Over-eager behavior on GUI computer use tasks (Anthropic) 13.3
- Anthropic automated behavioral audit
- Petri
- UK AISI alignment and monitorability evaluations
- Destructive production evaluation (Anthropic) 0.3
- Destructive actions (Anthropic)
- Adherence to its constitution (Anthropic) 1.02
- MASK 95.4
- Refusal to assist with AI safety R&D (Anthropic) 18.7
- Self-preference bias (Anthropic)
Monitorability
Bio and chem risk
Cyber risk
AI R&D risk
- Kernels task (Anthropic) 399.4
- Time series forecasting task (Anthropic) 4.55
- LLM training task (Anthropic) 51.9
- Quadruped reinforcement learning task (Anthropic) 30.9
- Novel compiler task (Anthropic) 77.2
- Internal AI research evaluation suite 2 0.65
- Internal model use survey (Anthropic) 5.6
- Anthropic ECI (AECI)
- Key insight rediscovery on an unpublished ML task (external testing) 80