Model Comparison

Claude Mythos Preview vs Claude Fable 5Which is better in 2026?

Claude Fable 5 shows notably better performance in the majority of benchmarks. Claude Fable 5 is 2.5x cheaper per token.

Verdict: Claude Mythos Preview vs Claude Fable 5 — which is better?

Claude Mythos Preview (by Anthropic) and Claude Fable 5 (by Anthropic) are two of the AI models people compare most. Here is how they stack up on benchmarks, price and capabilities, and which one to pick in 2026.

Claude Mythos Preview outperforms in 1 benchmarks (Humanity's Last Exam), while Claude Fable 5 is better at 3 benchmarks (OSWorld-Verified, SWE-Bench Pro, SWE-Bench Verified). Claude Fable 5 shows notably better performance in the majority of benchmarks.

On price, Claude Fable 5 is roughly 2.5x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Choose Claude Mythos Preview if…

  • you want predictable pricing at $25.00/M input and $125.00/M output

Choose Claude Fable 5 if…

  • you want the strongest raw capability — it leads on 3 of 4 shared benchmarks
  • cost matters — it's about 2.5x cheaper per token
Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

4 benchmarks

Claude Mythos Preview outperforms in 1 benchmarks (Humanity's Last Exam), while Claude Fable 5 is better at 3 benchmarks (OSWorld-Verified, SWE-Bench Pro, SWE-Bench Verified).

Claude Fable 5 shows notably better performance in the majority of benchmarks.

Thu Jun 18 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

Claude Fable 5 costs less

For input processing, Claude Mythos Preview ($25.00/1M tokens) is 2.5x more expensive than Claude Fable 5 ($10.00/1M tokens).

For output processing, Claude Mythos Preview ($125.00/1M tokens) is 2.5x more expensive than Claude Fable 5 ($50.00/1M tokens).

In conclusion, Claude Mythos Preview is more expensive than Claude Fable 5.*

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

Lowest available price from all providers
Thu Jun 18 2026 • llm-stats.com
Anthropic
Claude Mythos Preview
Input tokens$25.00
Output tokens$125.00
Best providerAnthropic
Anthropic
Claude Fable 5
Input tokens$10.00
Output tokens$50.00
Best providerAnthropic
Notice missing or incorrect data?Start an Issue→

Context Window

Maximum input and output token capacity

Only Claude Fable 5 specifies input context (1,000,000 tokens). Only Claude Fable 5 specifies output context (128,000 tokens).

Anthropic
Claude Mythos Preview
Input- tokens
Output- tokens
Anthropic
Claude Fable 5
Input1,000,000 tokens
Output128,000 tokens
Thu Jun 18 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

Both Claude Mythos Preview and Claude Fable 5 support multimodal inputs.

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

Claude Mythos Preview

Text
Images
Audio
Video

Claude Fable 5

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Claude Mythos Preview

Proprietary

Closed source

Claude Fable 5

Proprietary

Closed source

Release Timeline

When each model was launched

Neither model specifies a release date.

Unable to compare the release dates of the models.

No release dates available

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. Claude Fable 5 is available from Anthropic.

Claude Mythos Preview

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

Claude Fable 5

anthropic logo
Anthropic
Input Price:Input: $10.00/1MOutput Price:Output: $50.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Anthropic
Higher Humanity's Last Exam score (64.7% vs 64.5%)
Anthropic
Larger context window (1,000,000 tokens)
Less expensive input tokens
Less expensive output tokens
Higher OSWorld-Verified score (85.0% vs 79.6%)
Higher SWE-Bench Pro score (80.0% vs 77.8%)
Higher SWE-Bench Verified score (95.0% vs 93.9%)

Detailed Comparison

AI Model Comparison Table
Feature
Anthropic
Claude Mythos Preview
Anthropic
Claude Fable 5

FAQ

Common questions about Claude Mythos Preview vs Claude Fable 5.

Which is better, Claude Mythos Preview or Claude Fable 5?

Claude Fable 5 shows notably better performance in the majority of benchmarks. Claude Mythos Preview is made by Anthropic and Claude Fable 5 is made by Anthropic. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.

How does Claude Mythos Preview compare to Claude Fable 5 in benchmarks?

Claude Mythos Preview scores CyBench: 100.0%, USAMO25: 97.6%, GPQA: 94.6%, SWE-Bench Verified: 93.9%, CharXiv-R: 93.2%. Claude Fable 5 scores SWE-Bench Verified: 95.0%, FrontierSWE: 90.0%, OSWorld-Verified: 85.0%, Terminal-Bench 2.1: 84.3%, SWE-Bench Pro: 80.0%.

Is Claude Mythos Preview cheaper than Claude Fable 5?

Claude Fable 5 is 2.5x cheaper for input tokens. Claude Mythos Preview costs $25.00/M input and $125.00/M output via anthropic. Claude Fable 5 costs $10.00/M input and $50.00/M output via anthropic.

What are the context window sizes for Claude Mythos Preview and Claude Fable 5?

Claude Mythos Preview supports an unknown number of tokens and Claude Fable 5 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 Claude Fable 5?

Key differences include input pricing ($25.00 vs $10.00/M). See the full comparison above for benchmark-by-benchmark results.

Related comparisons