Qwen2-72B: benchmark scores, price and ranking
Qwen2-72B from Alibaba ranks #208 of 743 LLMs on the LLMs Tiger aggregate benchmark score (50.1), based on 2 benchmark results captured up to 2026-10-13.
- Organisation
- Alibaba
- Type
- Open-weight / local model
- Open weights
- Yes
- Released
- 2024-06-07 (source: epoch)
- Aggregate rank
- #208 of 743 (score 50.1)
Across the 2 benchmarks where at least ten models are scored, Qwen2-72B is in the top 10% on 0 and in the top half on 1.
Qwen2-72B benchmark results
| Benchmark | Score | Rank | Source | Captured |
|---|---|---|---|---|
| GSM8K | 89.5% | #7 of 17 | HuggingFace GSM8K leaderboard | 2026-10-13 |
| Epoch ECI | 125 | #113 of 204 | Epoch AI Benchmarking Hub | 2026-10-13 |
About Qwen2-72B
Qwen2-72B is an open-weight model that can run on your own hardware from Alibaba. It was released on 2024-06-07, according to Epoch AI. No API price is listed for it yet. We hold 2 benchmark results for it across 1 area, and none is in the top tenth of its board.
Where Qwen2-72B stands
On our aggregate score, Qwen2-72B is #208 of 743 ranked models, around the middle of the table. Its score is 50.1; the scale is centred on 50, so it sits 0.1 points above the typical model. That beats 72% of the ranked field. Among the 74 ranked Alibaba models it is #13. The next one up is ollama/Qwen2.5.1-Coder-7B-Instruct-GGUF:Q8_0-32k at 50.4. The next one down is ollama/qwen2.5-coder:14b at 50.1.
Qwen2-72B, benchmark by benchmark
GSM8K puts Qwen2-72B at 89.5%, #7 of 17. That beats 59% of the models tested, but 10.1 points short of mimo-v2.5-pro (99.6%). The results either side are Phi-3-medium-4k-instruct (91.0%) and DeepSeek-V3 (89.3%). It covers grade-school math word problems. The board median is 86.9%, so Qwen2-72B is 2.6 points above it. Source: HuggingFace GSM8K leaderboard, captured 2026-10-13.
Qwen2-72B lands below the middle on Epoch ECI: 125, #113 of 204, with 55% of the field scoring higher. Qwen 3.8 Max leads at 156; the closest result above is Llama 3.2 90B at 126. It covers Epoch Capabilities Index: Epoch's own aggregate of ~40 benchmarks. The board median is 127, so Qwen2-72B is 2 points below it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.
Strengths and weaknesses
General knowledge and chat: solid, ahead of 52% of the field on average across 2 benchmarks. Its best board here is GSM8K (#7 of 17) and its weakest is Epoch ECI (#113 of 204).
Release history
The Alibaba model released before it was qwen1.5-32b-chat on 2024-04-03, which scores 45.7. The next one was qwen2-72b-instruct on 2024-06-07, at 43.9.
Reading these numbers
The 2 scores on this page come from 2 sources: Epoch AI Benchmarking Hub (1), HuggingFace GSM8K leaderboard (1). No official leaderboard supplied any of them, so treat them as third-party measurements. With 2 results the aggregate rank can move a lot when one new score arrives.
Models ranked nearby
- #205 gpt-4.5-preview (50.2)
- #206 TTS(Bo16) (50.2)
- #207 gpt-4-1106-preview (50.2)
- #209 Muse Wonder (max) (50.1)
- #210 Claude Code + GLM-5.3-Flash (50.1)
- #211 ollama/qwen2.5-coder:14b (50.1)
More from Alibaba
- Qwen 3.6 Max (Preview) (#25, 54.1)
- Qwen3.8 Max (xhigh) (#37, 53.2)
- Qwen3.7 Max (#71, 52.3)
- ollama/qwen2.5-coder:32b (#93, 51.9)
- Qwen3 235B A22B diff, no think, Alibaba API (#122, 51.5)
- Qwen2.5-Coder-14B-Instruct (#135, 51.3)
Compare it on the live leaderboard → · How the aggregate score works