The AI arena is free today

Open Superagent

Codestral-22B vs Hy4 flash

Hy4 flash leads the LLM Stats Score 40.8 to -0.5.

Mistral AI · Tencent · Updated for 2026

Which is better?

Hy4 flash leads the overall LLM Stats Score 40.8 to -0.5, ranking #84 overall.

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

Choose Codestral-22B

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

Choose Hy4 flash

  • overall performance matters — it scores 40.8 and ranks #84 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you want the most recent training data — it shipped Nov 2026

At a glance

The differences that matter most.

Core performance indexes
-0.5
#377
40.8
#84
-0.7
#368
40.4
#77
2.3
#271
23.5
#107
Cost, coverage & limits
Benchmark wins
—
—
Input price
— / M
$0.07 / M
Output price
— / M
$0.28 / M
Context window
—
960,000

Individual benchmarks

7 reported for Codestral-22B · 9 for Hy4 flash

No common benchmarks found

Codestral-22B and Hy4 flashdon'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

Model Size

Parameter count comparison

201.8B diff

Hy4 flash has 201.8B more parameters than Codestral-22B, making it 909.0% larger.

Mistral AI
Codestral-22B
22.2Bparameters
Tencent
Hy4 flash
224.0Bparameters
22.2B
Codestral-22B
224.0B
Hy4 flash

Context Window

Maximum input and output token capacity

Only Hy4 flash specifies input context (960,000 tokens). Only Hy4 flash specifies output context (64,000 tokens).

Mistral AI
Codestral-22B
Input- tokens
Output- tokens
Tencent
Hy4 flash
Input960,000 tokens
Output64,000 tokens
Tue Nov 17 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Hy4 flash supports multimodal inputs, whereas Codestral-22B does not.

Hy4 flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

Codestral-22B

Text
Images
Audio
Video

Hy4 flash

Text
Images
Audio
Video

Release Timeline

When each model was launched

Codestral-22B was released on 2024-05-29, while Hy4 flash was released on 2026-11-16.

Hy4 flash is 30 months newer than Codestral-22B.

Codestral-22B

May 29, 2024

2.5 years ago

Hy4 flash

Nov 16, 2026

1 days ago

2.5yr newer

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

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Codestral-22B and Hy4 flash side-by-side, then vote on the output you prefer.

Codestral-22B
✓ Preferred
Hy4 flash
Open in Playground

FAQ

Common questions about Codestral-22B vs Hy4 flash.

Which is better, Codestral-22B or Hy4 flash?

Hy4 flash leads the LLM Stats Score 40.8 to -0.5. Codestral-22B is made by Mistral AI and Hy4 flash is made by Tencent. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Codestral-22B compare to Hy4 flash in benchmarks?

Codestral-22B scores HumanEvalFIM-Average: 91.6%, HumanEval: 81.1%, MBPP: 78.2%, Spider: 63.5%, HumanEval-Average: 61.5%. Hy4 flash scores MMMU-Pro: 75.8%, OSWorld 2.1 (partial): 68.1%, DeepSWE 1.1: 64.6%, APEX-Agents: 63.1%, Humanity's Last Exam (with tools): 55.2%.

What are the context window sizes for Codestral-22B and Hy4 flash?

Codestral-22B supports an unknown number of tokens and Hy4 flash supports 960K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Codestral-22B and Hy4 flash?

Key differences include LLM Stats Score (-0.5 vs 40.8), multimodal support (no vs yes), licensing (MNPL-0.1 vs Unknown). See the full comparison above for benchmark-by-benchmark results.

Who makes Codestral-22B and Hy4 flash?

Codestral-22B is developed by Mistral AI and Hy4 flash is developed by Tencent.