โ† Back to Model Hub/SIDE-BY-SIDE REVIEW
SHARE THIS:

DeepSeek V3.1 Terminus vs Qwen2.5 72B Instruct

How do these models stack up? Below is an expert side-by-side comparison of specifications, context window capacity, live pricing per million tokens, and standardized benchmark scores for DeepSeek V3.1 Terminus and Qwen2.5 72B Instruct.

DeepSeek

DeepSeek V3.1 Terminus

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

View Full Specs
Alibaba

Qwen2.5 72B Instruct

Qwen2.5 72B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabilities in coding and...

View Full Specs

Technical Specifications

SpecificationDeepSeek V3.1 TerminusQwen2.5 72B Instruct
ProviderDeepSeekAlibaba
Context Window163,840 tokens131,072 tokens
Agent SuitabilityN/AN/A
Time to First Token (TTFT)N/AN/A
Deployment Modelself hostableself hostable
Production Stabilitystablestable
API AvailableYesYes
Released Date2025-09-222024-09-19

API Pricing Comparison

Input Price per Million Tokens

DeepSeek V3.1 Terminus

$0.27

Qwen2.5 72B Instruct

$0.36

Output Price per Million Tokens

DeepSeek V3.1 Terminus

$0.95

Qwen2.5 72B Instruct

$0.40

Want to test both models live?

Run side-by-side prompt prompts in our dynamic Sandbox. Check execution speeds, latency metrics, and compute actual costs in real-time.

Benchmark Performance Metrics

Scores show the raw performance percentages verified across key evaluation suites. Higher bars indicate superior accuracy and capability in that domain.

MMLUGeneral knowledge & multi-task understanding
N/Avs8530.0%
DeepSeek V3.1 Terminus
Qwen2.5 72B Instruct
HumanEvalPython coding & logic synthesis
N/Avs8660.0%
DeepSeek V3.1 Terminus
Qwen2.5 72B Instruct
MATHComplex mathematical problem solving
N/Avs7460.0%
DeepSeek V3.1 Terminus
Qwen2.5 72B Instruct
GPQAGraduate-level expert reasoning
N/Avs4800.0%
DeepSeek V3.1 Terminus
Qwen2.5 72B Instruct
HellaSwagCommonsense reasoning and inference
N/Avs8820.0%
DeepSeek V3.1 Terminus
Qwen2.5 72B Instruct
MT-BenchMulti-turn conversation flow quality
N/Avs912.0%
DeepSeek V3.1 Terminus
Qwen2.5 72B Instruct

DeepSeek V3.1 Terminus Quirks & Gotchas

No developer gotchas reported.

Qwen2.5 72B Instruct Quirks & Gotchas

No developer gotchas reported.