New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Qwen2.5 Instruct (72B)
About Qwen2.5 Instruct (72B)
Qwen2.5 Instruct (72B) is an AI model developed by Qwen, in the language category, released in 2024, made available as an open-weights model with 72.7B params.
On this page you'll find Qwen2.5 Instruct (72B)'s full specifications, including 22 benchmark results. Review provider pricing and benchmark scores below, or compare Qwen2.5 Instruct (72B) head-to-head with other language models.
Links
Run Qwen2.5 Instruct (72B) locally — what to buy
Share this build ↗Sized to what Qwen2.5 Instruct (72B) actually needs (~8k context at Q4), not to the biggest GPU: Good = cheapest that runs it, Better = best value, Best = most headroom. Speed is a hardware estimate; anything past ~120 tok/s is shown as instant.
Software support
✓ measured · · compatible · — not supported. Informational only — speed is hardware-based.
Community
No reports yet. Own this model on some hardware? Be the first to confirm it runs.
No comments yet. Start the discussion.
Qwen2.5 Instruct (72B) benchmark scores▶
| Benchmark | Category | Score | Variant |
|---|---|---|---|
| HumanEval | code | 94% | instruct-pass@10-cited-tulu3 |
| HumanEval | code | 86.6% | instruct-cited-minimax-text |
| HumanEval+ | code | 90.8% | instruct-pass@10-cited-tulu3 |
| MBPP+ | code | 77% | instruct-plus-cited-minimax-text |
| AlpacaEval 2 | general | 47.7% | instruct-lc-win-cited-tulu3 |
| ArenaHard | general | 81.2% | instruct-cited-minimax-text |
| IFEval | general | 87.6% | instruct-cited-tulu3 |
| IFEval | general | 87.2% | instruct-avg-cited-minimax-text |
| MMLU | general | 86.1% | instruct-cited-minimax-text |
| MMLU | general | 85.5% | instruct-cited-tulu3 |
| MMLU-Pro | general | 71.1% | instruct-cited-minimax-text |
| GSM8K | math | 95.8% | instruct-cited-minimax-text |
| GSM8K | math | 89.5% | instruct-cited-tulu3 |
| MATH | math | 81.8% | instruct-cited-minimax-text |
| MATH | math | 74.3% | instruct-cited-tulu3 |
| BIG-Bench Hard | reasoning | 67.2% | instruct-cited-tulu3 |
| DROP | reasoning | 85% | instruct-f1-cited-minimax-text |
| DROP | reasoning | 34.2% | instruct-cited-tulu3 |
| GPQA Diamond | reasoning | 49% | instruct-diamond-cited-minimax-text |
| C-SimpleQA | safety | 52.2% | instruct-cited-minimax-text |
| SimpleQA | safety | 10.3% | instruct-cited-minimax-text |
| TruthfulQA | safety | 69.9% | instruct-cited-tulu3 |
More models like Qwen2.5 Instruct (72B)
Frequently asked questions
What is Qwen2.5 Instruct (72B)? ▶
Qwen2.5 Instruct (72B) is an AI model developed by Qwen, in the language category, released in 2024. It is tracked on GenAIList with its specifications, benchmark scores and provider pricing.
Who created Qwen2.5 Instruct (72B)? ▶
Qwen2.5 Instruct (72B) was developed by Qwen and released in 2024.
Is Qwen2.5 Instruct (72B) open source or proprietary? ▶
Qwen2.5 Instruct (72B) ships as an open-weights model: you can download and self-host the weights, though the licence may place some restrictions on use.
How much does Qwen2.5 Instruct (72B) cost? ▶
Pricing for Qwen2.5 Instruct (72B) depends on the provider. See the providers table on this page for the latest API rates.
How does Qwen2.5 Instruct (72B) perform on benchmarks? ▶
Qwen2.5 Instruct (72B) is benchmarked across 22 evaluations on GenAIList, including HumanEval (94%). See the full benchmark table below and compare it with other models.
No videos yet. Know a good one? Add it below.
Know a great video about Qwen2.5 Instruct (72B)?
Add YouTube Video
Add Tweet/Discussion
Report an Issue
Help us maintain accurate information in our database.
Suggest an Edit
Tell us what needs to be changed or corrected for