The AI arena is free today

Open Superagent

Claude Mythos Preview vs DeepSeek-V4.1-Flash

Claude Mythos Preview and DeepSeek-V4.1-Flash are closely matched at 54.9 and 51.8 on the LLM Stats Score. DeepSeek-V4.1-Flash is 151.5x cheaper per token.

Anthropic · DeepSeek · Updated for 2026

Which is better?

Claude Mythos Preview and DeepSeek-V4.1-Flash are closely matched on the overall LLM Stats Score at 54.9 and 51.8.

In the 3 individual benchmarks reported for both models, Claude Mythos Preview wins 2; this is a narrower head-to-head signal than the composite indexes.

On price, DeepSeek-V4.1-Flash is roughly 151.5x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Claude Mythos Preview

  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 3 exact shared results

Choose DeepSeek-V4.1-Flash

  • cost matters — it's about 151.5x cheaper per token
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Claude Mythos Preview
Anthropic
DeepSeek-V4.1-Flash
DeepSeek
Core performance indexes
LLM Stats Score
54.9
#4
51.8
#13
Reasoning
55.8
#2
48.9
#18
Coding
44.5
#4
44.2
#5
Agents
36.2
#17
41.1
#4
Cost, coverage & limits
Benchmark wins
2 of 3
1 of 3
Input price
$25.00 / M
$0.22 / M
Output price
$125.00 / M
$0.66 / M
Context window
—
1,040,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

4 shared
Index
Claude Mythos Preview
DeepSeek-V4.1-Flash
Math
47.0#1
35.2#43
Vision
39.3#3
29.5#31
Multimodal
37.4#5
34.3#13
Safety
17.1#8
21.8#3
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

16 reported for Claude Mythos Preview · 20 for DeepSeek-V4.1-Flash

3 shared

Claude Mythos Preview outperforms in 2 benchmarks (GPQA, Humanity's Last Exam), while DeepSeek-V4.1-Flash is better at 1 benchmark (CyberGym).

Claude Mythos Preview shows notably better performance in the majority of benchmarks.

Sun Sep 20 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

DeepSeek-V4.1-Flash costs less

For input processing, Claude Mythos Preview ($25.00/1M tokens) is 113.6x more expensive than DeepSeek-V4.1-Flash ($0.22/1M tokens).

For output processing, Claude Mythos Preview ($125.00/1M tokens) is 189.4x more expensive than DeepSeek-V4.1-Flash ($0.66/1M tokens).

In conclusion, Claude Mythos Preview is more expensive than DeepSeek-V4.1-Flash.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Sun Sep 20 2026 • llm-stats.com
Anthropic
Claude Mythos Preview
Input tokens$25.00
Output tokens$125.00
Best providerAnthropic
DeepSeek
DeepSeek-V4.1-Flash
Input tokens$0.22
Output tokens$0.66
Best providerFireworks
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Only DeepSeek-V4.1-Flash specifies input context (1,040,000 tokens). Only DeepSeek-V4.1-Flash specifies output context (393,216 tokens).

Anthropic
Claude Mythos Preview
Input- tokens
Output- tokens
DeepSeek
DeepSeek-V4.1-Flash
Input1,040,000 tokens
Output393,216 tokens
Sun Sep 20 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Claude Mythos Preview and DeepSeek-V4.1-Flash support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Claude Mythos Preview

Text
Images
Audio
Video

DeepSeek-V4.1-Flash

Text
Images
Audio
Video

License

Usage and distribution terms

Claude Mythos Preview is licensed under a proprietary license, while DeepSeek-V4.1-Flash uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

Claude Mythos Preview

Proprietary

Closed source

DeepSeek-V4.1-Flash

MIT

Open weights

Release Timeline

When each model was launched

DeepSeek-V4.1-Flash was released on 2026-09-10, while Claude Mythos Preview's release date is not specified.

We can confirm DeepSeek-V4.1-Flash's release timeline, but cannot make a direct age comparison without Claude Mythos Preview's release date.

Claude Mythos Preview

—

DeepSeek-V4.1-Flash

Sep 10, 2026

1 weeks ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Provider Availability

Claude Mythos Preview is available from Anthropic. DeepSeek-V4.1-Flash is available from Fireworks, DeepInfra, DeepSeek, Novita.

Claude Mythos Preview

anthropic logo
Anthropic
Input Price:Input: $25.00/1MOutput Price:Output: $125.00/1M

DeepSeek-V4.1-Flash

fireworks logo
Fireworks
Input Price:Input: $0.22/1MOutput Price:Output: $0.66/1M
deepinfra logo
Deepinfra
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
deepseek logo
DeepSeek
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
novita logo
Novita
Input Price:Input: $0.30/1MOutput Price:Output: $1.20/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Judge for yourself.

Run your own prompts against Claude Mythos Preview and DeepSeek-V4.1-Flash side-by-side, then vote on the output you prefer.

Claude Mythos Preview
✓ Preferred
DeepSeek-V4.1-Flash
Open in Playground

FAQ

Common questions about Claude Mythos Preview vs DeepSeek-V4.1-Flash.

Which is better, Claude Mythos Preview or DeepSeek-V4.1-Flash?

Claude Mythos Preview and DeepSeek-V4.1-Flash are closely matched on the LLM Stats Score at 54.9 and 51.8. Claude Mythos Preview is made by Anthropic and DeepSeek-V4.1-Flash is made by DeepSeek. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude Mythos Preview compare to DeepSeek-V4.1-Flash in benchmarks?

Claude Mythos Preview scores CyBench: 100.0%, USAMO25: 97.6%, GPQA: 94.6%, SWE-Bench Verified: 93.9%, CharXiv-R: 93.2%. DeepSeek-V4.1-Flash scores CodeForces: 100.0%, GPQA: 90.9%, Terminal-Bench 2.1: 90.6%, BabyVision: 89.6%, CyberGym: 88.1%.

Is Claude Mythos Preview cheaper than DeepSeek-V4.1-Flash?

DeepSeek-V4.1-Flash is 113.6x cheaper for input tokens. Claude Mythos Preview costs $25.00/M input and $125.00/M output via anthropic. DeepSeek-V4.1-Flash costs $0.22/M input and $0.66/M output via fireworks.

What are the context window sizes for Claude Mythos Preview and DeepSeek-V4.1-Flash?

Claude Mythos Preview supports an unknown number of tokens and DeepSeek-V4.1-Flash supports 1.0M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Claude Mythos Preview and DeepSeek-V4.1-Flash?

Key differences include LLM Stats Score (54.9 vs 51.8), input pricing ($25.00 vs $0.22/M), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude Mythos Preview and DeepSeek-V4.1-Flash?

Claude Mythos Preview is developed by Anthropic and DeepSeek-V4.1-Flash is developed by DeepSeek.

Related comparisons