Model Comparison

ERNIE 4.5 vs LongCat-Flash-Thinking

LongCat-Flash-Thinking significantly outperforms across most benchmarks. LongCat-Flash-Thinking is 2.5x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

3 benchmarks

ERNIE 4.5 outperforms in 0 benchmarks, while LongCat-Flash-Thinking is better at 3 benchmarks (GPQA, MMLU-Pro, MMLU-Redux).

LongCat-Flash-Thinking significantly outperforms across most benchmarks.

Thu Apr 16 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

LongCat-Flash-Thinking costs less

For input processing, ERNIE 4.5 ($0.40/1M tokens) is 1.3x more expensive than LongCat-Flash-Thinking ($0.30/1M tokens).

For output processing, ERNIE 4.5 ($4.00/1M tokens) is 3.3x more expensive than LongCat-Flash-Thinking ($1.20/1M tokens).

In conclusion, ERNIE 4.5 is more expensive than LongCat-Flash-Thinking.*

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

Lowest available price from all providers
Thu Apr 16 2026 • llm-stats.com
Baidu
ERNIE 4.5
Input tokens$0.40
Output tokens$4.00
Best providerNovita
Meituan
LongCat-Flash-Thinking
Input tokens$0.30
Output tokens$1.20
Best providerMeituan
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

539.0B diff

LongCat-Flash-Thinking has 539.0B more parameters than ERNIE 4.5, making it 2566.7% larger.

Baidu
ERNIE 4.5
21.0Bparameters
Meituan
LongCat-Flash-Thinking
560.0Bparameters
21.0B
ERNIE 4.5
560.0B
LongCat-Flash-Thinking

Context Window

Maximum input and output token capacity

Both models have the same input context window of 128,000 tokens. LongCat-Flash-Thinking can generate longer responses up to 128,000 tokens, while ERNIE 4.5 is limited to 65,536 tokens.

Baidu
ERNIE 4.5
Input128,000 tokens
Output65,536 tokens
Meituan
LongCat-Flash-Thinking
Input128,000 tokens
Output128,000 tokens
Thu Apr 16 2026 • llm-stats.com

License

Usage and distribution terms

ERNIE 4.5 is licensed under a proprietary license, while LongCat-Flash-Thinking uses MIT.

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

ERNIE 4.5

Proprietary

Closed source

LongCat-Flash-Thinking

MIT

Open weights

Release Timeline

When each model was launched

ERNIE 4.5 was released on 2025-06-25, while LongCat-Flash-Thinking was released on 2025-09-22.

LongCat-Flash-Thinking is 3 months newer than ERNIE 4.5.

ERNIE 4.5

Jun 25, 2025

9 months ago

LongCat-Flash-Thinking

Sep 22, 2025

6 months ago

2mo 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

Provider Availability

ERNIE 4.5 is available from Novita. LongCat-Flash-Thinking is available from Meituan.

ERNIE 4.5

novita logo
Novita
Input Price:Input: $0.40/1MOutput Price:Output: $4.00/1M

LongCat-Flash-Thinking

meituan logo
Meituan
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→

Key Takeaways

Baidu
Meituan
Less expensive input tokens
Less expensive output tokens
Has open weights
Higher GPQA score (81.5% vs 74.0%)
Higher MMLU-Pro score (82.6% vs 16.0%)
Higher MMLU-Redux score (89.3% vs 43.2%)

Detailed Comparison

AI Model Comparison Table
Feature
Baidu
ERNIE 4.5
Meituan
LongCat-Flash-Thinking

FAQ

Common questions about ERNIE 4.5 vs LongCat-Flash-Thinking

LongCat-Flash-Thinking significantly outperforms across most benchmarks. ERNIE 4.5 is made by Baidu and LongCat-Flash-Thinking is made by Meituan. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
ERNIE 4.5 scores GPQA: 74.0%, ARC-E: 60.7%, PIQA: 55.2%, Winogrande: 51.3%, CLUEWSC: 48.6%. LongCat-Flash-Thinking scores MATH-500: 99.2%, ZebraLogic: 95.5%, AIME 2024: 93.3%, AIME 2025: 90.6%, MMLU-Redux: 89.3%.
LongCat-Flash-Thinking is 1.3x cheaper for input tokens. ERNIE 4.5 costs $0.40/M input and $4.00/M output via novita. LongCat-Flash-Thinking costs $0.30/M input and $1.20/M output via meituan.
ERNIE 4.5 supports 128K tokens and LongCat-Flash-Thinking supports 128K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include input pricing ($0.40 vs $0.30/M), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.
ERNIE 4.5 is developed by Baidu and LongCat-Flash-Thinking is developed by Meituan.