Model Comparison

GLM-4.6 vs DeepSeek-V3.1

GLM-4.6 significantly outperforms across most benchmarks. DeepSeek-V3.1 is 2.0x cheaper per token.

Want to compare interactively?Try the playground

Performance Benchmarks

Comparative analysis across standard metrics

6 benchmarks

GLM-4.6 outperforms in 6 benchmarks (AIME 2025, BrowseComp, GPQA, Humanity's Last Exam, SWE-Bench Verified, Terminal-Bench), while DeepSeek-V3.1 is better at 0 benchmarks.

GLM-4.6 significantly outperforms across most benchmarks.

Wed Apr 22 2026 • llm-stats.com

Arena Performance

Human preference votes

Pricing Analysis

Price comparison per million tokens

DeepSeek-V3.1 costs less

For input processing, GLM-4.6 ($0.55/1M tokens) is 2.0x more expensive than DeepSeek-V3.1 ($0.27/1M tokens).

For output processing, GLM-4.6 ($2.00/1M tokens) is 2.0x more expensive than DeepSeek-V3.1 ($1.00/1M tokens).

In conclusion, GLM-4.6 is more expensive than DeepSeek-V3.1.*

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

Lowest available price from all providers
Wed Apr 22 2026 • llm-stats.com
Zhipu AI
GLM-4.6
Input tokens$0.55
Output tokens$2.00
Best providerFireworks
DeepSeek
DeepSeek-V3.1
Input tokens$0.27
Output tokens$1.00
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue→

Model Size

Parameter count comparison

314.0B diff

DeepSeek-V3.1 has 314.0B more parameters than GLM-4.6, making it 88.0% larger.

Zhipu AI
GLM-4.6
357.0Bparameters
DeepSeek
DeepSeek-V3.1
671.0Bparameters
357.0B
GLM-4.6
671.0B
DeepSeek-V3.1

Context Window

Maximum input and output token capacity

DeepSeek-V3.1 accepts 163,840 input tokens compared to GLM-4.6's 131,072 tokens. DeepSeek-V3.1 can generate longer responses up to 163,840 tokens, while GLM-4.6 is limited to 131,072 tokens.

Zhipu AI
GLM-4.6
Input131,072 tokens
Output131,072 tokens
DeepSeek
DeepSeek-V3.1
Input163,840 tokens
Output163,840 tokens
Wed Apr 22 2026 • llm-stats.com

Input Capabilities

Supported data types and modalities

GLM-4.6 supports multimodal inputs, whereas DeepSeek-V3.1 does not.

GLM-4.6 can handle both text and other forms of data like images, making it suitable for multimodal applications.

GLM-4.6

Text
Images
Audio
Video

DeepSeek-V3.1

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under MIT.

Both models share the same licensing terms, providing consistent usage rights.

GLM-4.6

MIT

Open weights

DeepSeek-V3.1

MIT

Open weights

Release Timeline

When each model was launched

GLM-4.6 was released on 2025-09-30, while DeepSeek-V3.1 was released on 2025-01-10.

GLM-4.6 is 9 months newer than DeepSeek-V3.1.

GLM-4.6

Sep 30, 2025

6 months ago

8mo newer
DeepSeek-V3.1

Jan 10, 2025

1.3 years 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

GLM-4.6 is available from Fireworks, DeepInfra. DeepSeek-V3.1 is available from DeepInfra, Novita.

GLM-4.6

fireworks logo
Fireworks
Input Price:Input: $0.55/1MOutput Price:Output: $2.19/1M
deepinfra logo
Deepinfra
Input Price:Input: $0.60/1MOutput Price:Output: $2.00/1M

DeepSeek-V3.1

deepinfra logo
Deepinfra
Input Price:Input: $0.27/1MOutput Price:Output: $1.00/1M
novita logo
Novita
Input Price:Input: $0.27/1MOutput Price:Output: $1.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion→

Key Takeaways

Zhipu AI
Supports multimodal inputs
Higher AIME 2025 score (93.9% vs 49.8%)
Higher BrowseComp score (45.1% vs 30.0%)
Higher GPQA score (81.0% vs 74.9%)
Higher Humanity's Last Exam score (17.2% vs 15.9%)
Higher SWE-Bench Verified score (68.0% vs 66.0%)
Higher Terminal-Bench score (40.5% vs 31.3%)
DeepSeek
Larger context window (163,840 tokens)
Less expensive input tokens
Less expensive output tokens

Detailed Comparison

AI Model Comparison Table
Feature
Zhipu AI
GLM-4.6
DeepSeek
DeepSeek-V3.1

FAQ

Common questions about GLM-4.6 vs DeepSeek-V3.1

GLM-4.6 significantly outperforms across most benchmarks. GLM-4.6 is made by Zhipu AI and DeepSeek-V3.1 is made by DeepSeek. The best choice depends on your use case — compare their benchmark scores, pricing, and capabilities above.
GLM-4.6 scores AIME 2025: 93.9%, LiveCodeBench v6: 82.8%, GPQA: 81.0%, SWE-Bench Verified: 68.0%, BrowseComp: 45.1%. DeepSeek-V3.1 scores SimpleQA: 93.4%, MMLU-Redux: 91.8%, MMLU-Pro: 83.7%, GPQA: 74.9%, CodeForces: 69.7%.
DeepSeek-V3.1 is 2.0x cheaper for input tokens. GLM-4.6 costs $0.55/M input and $2.00/M output via fireworks. DeepSeek-V3.1 costs $0.27/M input and $1.00/M output via deepinfra.
GLM-4.6 supports 131K tokens and DeepSeek-V3.1 supports 164K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.
Key differences include context window (131K vs 164K), input pricing ($0.55 vs $0.27/M), multimodal support (yes vs no). See the full comparison above for benchmark-by-benchmark results.
GLM-4.6 is developed by Zhipu AI and DeepSeek-V3.1 is developed by DeepSeek.