The AI arena is free today

Open Superagent

Claude Mythos 5.2 vs Step3-VL-10B

Claude Mythos 5.2 leads the LLM Stats Score 59.3 to 24.9.

Anthropic · StepFun · Updated for 2026

Which is better?

Claude Mythos 5.2 leads the overall LLM Stats Score 59.3 to 24.9, ranking #2 overall.

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

Choose Claude Mythos 5.2

  • overall performance matters — it scores 59.3 and ranks #2 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Nov 2026

Choose Step3-VL-10B

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
59.3
#2
24.9
#200
53.4
#7
24.9
#196
Cost, coverage & limits
Benchmark wins
—
—
Input price
$8.00 / M
— / M
Output price
$40.00 / M
— / M
Context window
1,000,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Claude Mythos 5.2
Step3-VL-10B
30.8#39
16.0#115
30.6#37
19.6#95
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

9 reported for Claude Mythos 5.2 · 6 for Step3-VL-10B

No common benchmarks found

Claude Mythos 5.2 and Step3-VL-10Bdon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Claude Mythos 5.2 specifies input context (1,000,000 tokens). Only Claude Mythos 5.2 specifies output context (128,000 tokens).

Anthropic
Claude Mythos 5.2
Input1,000,000 tokens
Output128,000 tokens
StepFun
Step3-VL-10B
Input- tokens
Output- tokens
Mon Nov 16 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Claude Mythos 5.2 and Step3-VL-10B support multimodal inputs.

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

Claude Mythos 5.2

Text
Images
Audio
Video

Step3-VL-10B

Text
Images
Audio
Video

License

Usage and distribution terms

Claude Mythos 5.2 is licensed under a proprietary license, while Step3-VL-10B uses Apache 2.0.

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

Claude Mythos 5.2

Proprietary

Closed source

Step3-VL-10B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Claude Mythos 5.2 was released on 2026-11-09, while Step3-VL-10B was released on 2026-01-15.

Claude Mythos 5.2 is 10 months newer than Step3-VL-10B.

Claude Mythos 5.2

Nov 9, 2026

1 weeks ago

9mo newer
Step3-VL-10B

Jan 15, 2026

10 months ago

Knowledge Cutoff

When training data ends

Claude Mythos 5.2 has a documented knowledge cutoff of 2026-06-01, while Step3-VL-10B's cutoff date is not specified.

We can confirm Claude Mythos 5.2's training data extends to 2026-06-01, but cannot make a direct comparison without Step3-VL-10B's cutoff date.

Claude Mythos 5.2

Jun 2026

Step3-VL-10B

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Claude Mythos 5.2 and Step3-VL-10B side-by-side, then vote on the output you prefer.

Claude Mythos 5.2
✓ Preferred
Step3-VL-10B
Open in Playground

FAQ

Common questions about Claude Mythos 5.2 vs Step3-VL-10B.

Which is better, Claude Mythos 5.2 or Step3-VL-10B?

Claude Mythos 5.2 leads the LLM Stats Score 59.3 to 24.9. Claude Mythos 5.2 is made by Anthropic and Step3-VL-10B is made by StepFun. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude Mythos 5.2 compare to Step3-VL-10B in benchmarks?

Claude Mythos 5.2 scores De novo protein binder design: 85.1%, Biomedical image analysis: 80.7%, Protocols Troubleshooting: 77.1%, Terminal-Bench-Science 0.1: 75.3%, Terminal-Bench 4.0: 70.5%. Step3-VL-10B scores MMBench: 91.8%, AIME 2025: 87.7%, MathVista: 84.0%, MMMU: 78.1%, MathVision: 70.8%.

What are the context window sizes for Claude Mythos 5.2 and Step3-VL-10B?

Claude Mythos 5.2 supports 1.0M tokens and Step3-VL-10B supports an unknown number of 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 5.2 and Step3-VL-10B?

Key differences include LLM Stats Score (59.3 vs 24.9), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude Mythos 5.2 and Step3-VL-10B?

Claude Mythos 5.2 is developed by Anthropic and Step3-VL-10B is developed by StepFun.