Skip to main content
Van Data Team
Legacy modelAlibaba Qwen

Qwen2 72B Instruct benchmarks, pricing and specs

Qwen2 72B Instruct is an Alibaba Qwen model released on June 7, 2024 that takes text input and produces text. It is now listed as a legacy model. Its price is not published and accepts up to 128,000 tokens of context. It scores 1262 Elo on Arena Text (Arena, measured October 8, 2026).

Context window
128K
Arena Text
1262 Elo

Data verified October 12, 2026 · Dataset 2026-10-12

Share this

Key facts

Provider
Alibaba Qwen
Model family
Qwen2
Release date
June 7, 2024
Status
Legacy
Access
open weights
API model id
Not reported
Context window
128,000 tokens
Max output
Not reported
Input
text
Output
text
Task families
text
Declared capabilities
reasoning

Qwen2 72B Instruct pricing

UnitPrice (USD)TierAppliesSource
1M input tokensNot reportedstandardCurrent
1M output tokensNot reportedstandardCurrent
1M input tokensNot reportedcachedCurrent

Independent benchmark results

Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Alibaba Qwen's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.

BenchmarkScoreRankMeasuredSource
Arena Text1262 EloNot rankedOctober 8, 2026Arena · 2026-10-12
GPQA Diamond40.8%Not rankedOctober 12, 2026Epoch AI · 2026-10-12

Strengths, cautions and best uses

Strengths

  • Qwen2 72B Instruct records open-weight access for text inputs and a published 128,000-token context window

Cautions

  • This record is marked legacy; confirm current availability and migration requirements before adoption

Best for

  • Historical larger private text deployments

Alternatives to Qwen2 72B Instruct

The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.

Other Qwen2 models

Qwen2 72B Instruct FAQ

What is the context window of Qwen2 72B Instruct?

Qwen2 72B Instruct accepts up to 128,000 tokens of context. That ranks #40 of 45 current text models by context length.

How does Qwen2 72B Instruct score on independent benchmarks?

Qwen2 72B Instruct scores 1262 Elo on Arena Text (Arena, measured October 8, 2026) and 40.8% on GPQA Diamond (Epoch AI, measured October 12, 2026). These are independent evaluations, not Alibaba Qwen's own launch figures.

Is Qwen2 72B Instruct open source or API only?

Qwen2 72B Instruct is released as open weights that you can run yourself.

What are the best alternatives to Qwen2 72B Instruct?

The closest current alternatives by price and measured performance are DeepSeek-R1 (136 points higher on Arena Text, 1398 vs 1262), Gemini 2.5 Pro (183 points higher on Arena Text, 1445 vs 1262), GPT-4.1 (153 points higher on Arena Text, 1415 vs 1262) and GPT-4.1 mini (121 points higher on Arena Text, 1383 vs 1262).

Sources

Cite this page

Van Data Team. "Qwen2 72B Instruct Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/qwen2-72b-instruct

Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.

Production evaluation

Deciding whether Qwen2 72B Instruct fits your workload?

Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.

  • Evaluation cases and acceptance thresholds tied to real work
  • Model routing, fallbacks and cost controls
Compare all modelsDiscuss your evaluation