benchlm.ai

Claude Mythos Preview

AnthropicCurrentReleased Apr 7, 2026
Overall Score
84#5 of 105
Arena Elo
N/A
Categories Ranked
3of 8
Price (1M tokens)
$25 in / $125 out
Speed
N/A
Context
1M
ProprietaryReasoning
Confidence
preview

According to BenchLM.ai, Claude Mythos Preview ranks #5 out of 105 models with an overall score of 84/100. This places it among the top tier of AI models available in 2026, competing directly with the strongest models from leading AI labs.

Claude Mythos Preview is a proprietary model with a 1M token context window. It uses explicit chain-of-thought reasoning, which typically improves performance on math and complex reasoning tasks at the cost of higher latency and token usage.

This profile currently has 8 of 126 tracked benchmarks. BenchLM only exposes non-generated benchmark rows publicly, so missing categories stay blank until a sourced evaluation is available.

Its strongest category is Multimodal & Grounded (#5), while its weakest is Multilingual (#6). This performance profile makes it particularly strong for screenshots, documents, charts, and grounded multimodal workflows.

Ranking Distribution

Category rank across 3 benchmark categories — sorted by best rank

Category Performance

Scores across all benchmark categories (0-100 scale)

Category Breakdown

Agentic

#6
80.9/ 100
Weight: 22%2 benchmarks
Terminal-Bench 2.0BrowseCompOSWorld-Verified

Coding

0.0/ 100
Weight: 20%2 benchmarks
SWE-bench VerifiedLiveCodeBenchSWE-bench ProSWE-RebenchterminalBench2

Reasoning

0.0/ 100
Weight: 17%0 benchmarks
MuSRLongBench v2MRCRv2ARC-AGI-2

Knowledge

0.0/ 100
Weight: 12%3 benchmarks
GPQASuperGPQAMMLU-ProHLEFrontierScienceSimpleQA

Math

0.0/ 100
Weight: 5%0 benchmarks
AIME 2025BRUMO 2025MATH-500

Multilingual

#6
92.7/ 100
Weight: 7%0 benchmarks
MGSMMMLU-ProX

Multimodal

#5
92.7/ 100
Weight: 12%1 benchmark
MMMU-ProOfficeQA Pro

Inst. Following

0.0/ 100
Weight: 5%0 benchmarks
IFEval

Benchmark Details

Only benchmark rows with an attached exact-source record are shown here. Source-unverified manual rows and generated rows are hidden from model pages.

Compare This Model

See how Claude Mythos Preview stacks up against similar models

Claude Opus 4.6Anthropic
85
Claude Sonnet 4.6Anthropic
81
Claude Opus 4.5Anthropic
76
Gemini 3.1 ProGoogle
87
Grok 4.1xAI
85

Frequently Asked Questions

How does Claude Mythos Preview perform overall in AI benchmarks?

Claude Mythos Preview ranks #5 out of 105 models with an overall score of 84. It is created by Anthropic and features a 1M context window.

Is Claude Mythos Preview good for knowledge and understanding?

Claude Mythos Preview has visible benchmark coverage in knowledge and understanding, but BenchLM does not currently assign it a global category rank there.

Is Claude Mythos Preview good for coding and programming?

Claude Mythos Preview has visible benchmark coverage in coding and programming, but BenchLM does not currently assign it a global category rank there.

Is Claude Mythos Preview good for agentic tool use and computer tasks?

Claude Mythos Preview ranks #6 out of 105 models in agentic tool use and computer tasks benchmarks with an average score of 80.9. It is among the top performers in this category.

Is Claude Mythos Preview good for multimodal and grounded tasks?

Claude Mythos Preview ranks #5 out of 105 models in multimodal and grounded tasks benchmarks with an average score of 92.7. It is among the top performers in this category.

Does Claude Mythos Preview have full benchmark coverage on BenchLM?

Not yet. Claude Mythos Preview currently has 8 published benchmark scores out of the 126 benchmarks BenchLM tracks. BenchLM only exposes non-generated public benchmark rows, so missing categories stay blank until a sourced evaluation is available.

What is the context window size of Claude Mythos Preview?

Claude Mythos Preview has a context window of 1M, which determines how much text it can process in a single interaction.

Related Resources

More from Anthropic LLM Pricing Comparison BenchLM Methodology The AI Race Which LLM Should I Use? Benchmark Explainers
Last updated: April 7, 2026 · Runtime metrics stay blank until BenchLM has a sourced snapshot.

Weekly LLM Updates

New model releases, benchmark scores, and leaderboard changes. Every Friday.

Free. Your signup is stored with a derived country code for compliance routing.