The AI arena is free today

Open Superagent

Qwen2.5 72B Instruct vs Qwen3.8 Max

Qwen3.8 Max leads the LLM Stats Score 51.9 to 12.1. Qwen2.5 72B Instruct is 6.8x cheaper per token.

Alibaba Cloud / Qwen Team · Alibaba Cloud / Qwen Team · Updated for 2026

Which is better?

Qwen3.8 Max leads the overall LLM Stats Score 51.9 to 12.1, ranking #11 overall.

In the 1 individual benchmarks reported for both models, Qwen3.8 Max wins 1; this is a narrower head-to-head signal than the composite indexes.

On price, Qwen2.5 72B Instruct is roughly 6.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

Qwen3.8 Max also accepts a larger context window (256,000 input tokens), making it the stronger choice for long documents and large codebases.

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

Choose Qwen2.5 72B Instruct

  • cost matters — it's about 6.8x cheaper per token

Choose Qwen3.8 Max

  • overall performance matters — it scores 51.9 and ranks #11 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you process long inputs — it offers a 256,000 token context window
  • you want the most recent training data — it shipped Aug 2026

At a glance

The differences that matter most.

Core performance indexes
12.1
#252
51.9
#11
12.2
#244
50.6
#11
9.2
#175
39.6
#14
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
$0.35 / M
$1.65 / M
Output price
$0.40 / M
$4.95 / M
Context window
131,072
256,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Qwen2.5 72B Instruct
Qwen3.8 Max
17.8#191
33.8#52
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for Qwen2.5 72B Instruct · 42 for Qwen3.8 Max

1 shared

Qwen2.5 72B Instruct outperforms in 0 benchmarks, while Qwen3.8 Max is better at 1 benchmark (GPQA).

Qwen3.8 Max significantly outperforms across most benchmarks.

Sun Sep 13 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Qwen2.5 72B Instruct costs less

For input processing, Qwen2.5 72B Instruct ($0.35/1M tokens) is 4.7x cheaper than Qwen3.8 Max ($1.65/1M tokens).

For output processing, Qwen2.5 72B Instruct ($0.40/1M tokens) is 12.4x cheaper than Qwen3.8 Max ($4.95/1M tokens).

In conclusion, Qwen3.8 Max is more expensive than Qwen2.5 72B Instruct.*

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

Lowest available price from all providers
Sun Sep 13 2026 • llm-stats.com
Alibaba Cloud / Qwen Team
Qwen2.5 72B Instruct
Input tokens$0.35
Output tokens$0.40
Best providerDeepinfra
Alibaba Cloud / Qwen Team
Qwen3.8 Max
Input tokens$1.65
Output tokens$4.95
Best providerDeepinfra
Notice missing or incorrect data?Start an Issue

Model Size

Parameter count comparison

2327.3B diff

Qwen3.8 Max has 2327.3B more parameters than Qwen2.5 72B Instruct, making it 3201.2% larger.

Alibaba Cloud / Qwen Team
Qwen2.5 72B Instruct
72.7Bparameters
Alibaba Cloud / Qwen Team
Qwen3.8 Max
2.4Tparameters
72.7B
Qwen2.5 72B Instruct
2400.0B
Qwen3.8 Max

Context Window

Maximum input and output token capacity

Qwen3.8 Max accepts 256,000 input tokens compared to Qwen2.5 72B Instruct's 131,072 tokens. Qwen3.8 Max can generate longer responses up to 256,000 tokens, while Qwen2.5 72B Instruct is limited to 8,192 tokens.

Alibaba Cloud / Qwen Team
Qwen2.5 72B Instruct
Input131,072 tokens
Output8,192 tokens
Alibaba Cloud / Qwen Team
Qwen3.8 Max
Input256,000 tokens
Output256,000 tokens
Sun Sep 13 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Qwen3.8 Max supports multimodal inputs, whereas Qwen2.5 72B Instruct does not.

Qwen3.8 Max can handle both text and other forms of data like images, making it suitable for multimodal applications.

Qwen2.5 72B Instruct

Text
Images
Audio
Video

Qwen3.8 Max

Text
Images
Audio
Video

License

Usage and distribution terms

Qwen2.5 72B Instruct is licensed under Qwen, while Qwen3.8 Max uses Qwen3.8-Max License.

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

Qwen2.5 72B Instruct

Qwen

Open weights

Qwen3.8 Max

Qwen3.8-Max License

Open weights

Release Timeline

When each model was launched

Qwen2.5 72B Instruct was released on 2024-09-19, while Qwen3.8 Max was released on 2026-08-02.

Qwen3.8 Max is 23 months newer than Qwen2.5 72B Instruct.

Qwen2.5 72B Instruct

Sep 19, 2024

2.0 years ago

Qwen3.8 Max

Aug 2, 2026

1 months ago

1.9yr 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

Qwen2.5 72B Instruct is available from DeepInfra, Hyperbolic, Fireworks, Together. Qwen3.8 Max is available from DeepInfra, Fireworks, Novita, Together.

Qwen2.5 72B Instruct

deepinfra logo
Deepinfra
Input Price:Input: $0.35/1MOutput Price:Output: $0.40/1M
hyperbolic logo
Hyperbolic
Input Price:Input: $0.40/1MOutput Price:Output: $0.40/1M
fireworks logo
Fireworks
Input Price:Input: $0.89/1MOutput Price:Output: $0.89/1M
together logo
Together
Input Price:Input: $1.20/1MOutput Price:Output: $1.20/1M

Qwen3.8 Max

deepinfra logo
Deepinfra
Input Price:Input: $1.65/1MOutput Price:Output: $4.95/1M
fireworks logo
Fireworks
Input Price:Input: $2.00/1MOutput Price:Output: $6.00/1M
novita logo
Novita
Input Price:Input: $2.00/1MOutput Price:Output: $6.00/1M
together logo
Together
Input Price:Input: $2.50/1MOutput Price:Output: $6.25/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against Qwen2.5 72B Instruct and Qwen3.8 Max side-by-side, then vote on the output you prefer.

Qwen2.5 72B Instruct
✓ Preferred
Qwen3.8 Max
Open in Playground

FAQ

Common questions about Qwen2.5 72B Instruct vs Qwen3.8 Max.

Which is better, Qwen2.5 72B Instruct or Qwen3.8 Max?

Qwen3.8 Max leads the LLM Stats Score 51.9 to 12.1. Qwen2.5 72B Instruct is made by Alibaba Cloud / Qwen Team and Qwen3.8 Max is made by Alibaba Cloud / Qwen Team. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Qwen2.5 72B Instruct compare to Qwen3.8 Max in benchmarks?

Qwen2.5 72B Instruct scores GSM8k: 95.8%, MT-Bench: 93.5%, MBPP: 88.2%, MMLU-Redux: 86.8%, HumanEval: 86.6%. Qwen3.8 Max scores PaperBench: 93.0%, MRCR v2 (8-needle): 92.9%, GPQA: 92.6%, VideoMME w sub.: 90.4%, RealWorldQA: 88.0%.

Is Qwen2.5 72B Instruct cheaper than Qwen3.8 Max?

Qwen2.5 72B Instruct is 4.7x cheaper for input tokens. Qwen2.5 72B Instruct costs $0.35/M input and $0.40/M output via deepinfra. Qwen3.8 Max costs $1.65/M input and $4.95/M output via deepinfra.

What are the context window sizes for Qwen2.5 72B Instruct and Qwen3.8 Max?

Qwen2.5 72B Instruct supports 131K tokens and Qwen3.8 Max supports 256K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Qwen2.5 72B Instruct and Qwen3.8 Max?

Key differences include LLM Stats Score (12.1 vs 51.9), context window (131K vs 256K), input pricing ($0.35 vs $1.65/M), multimodal support (no vs yes), licensing (Qwen vs Qwen3.8-Max License). See the full comparison above for benchmark-by-benchmark results.