AlibabaQwen2-72B
Qwen2-72B is an Alibaba open-weights model, released 7 Jun 2024. Its best configuration ranks #648 of 785 on the BenchLeader Index at 40.9 ±4.3, in the lower half. The ± is the point: 278 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in maths (43) and lowest in coding (32). Last measured 22 Oct 2026.
- Blended price
- –
- Output speed
- –
- First answer
- –
- Context
- 131k
- Full answer
- –
- Cost per run
- –
- Released
- 7 Jun 2024
- Overall index41
- Reasoning35
- Coding32
- Maths43
- Human preference41
- Composite37
How its index has moved
8 Sept 2026 to 18 Oct 2026The index is recomputed from scratch every day, so a line moves when a new benchmark result lands, when a publisher revises a score, or when the models it is normalised against change. Early movement usually means the score is still settling.
Benchmark results
See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| GPQA Diamond | 40.8%#246 | Epoch AI Benchmarking Hub | |
| Arena Hard Prompts | 1274#278 | Arena (LMArena) | |
| GPQA Diamond (AA)not in index | 37.1%#488 | Artificial Analysis | |
| Humanity's Last Exam (AA)not in index | 3.7%#577 | Artificial Analysis |
Coding
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| WeirdML | 11.3%#149 | WeirdML | |
| Arena Coding | 1297#279 | Arena (LMArena) |
Agents & tools
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| TheAgentCompanynot in index | 1.1%#14 | TheAgentCompany | |
| METR Time Horizonsnot in index | 29.9%#35 | METR |
Maths
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MATH Level 5 | 39.1%#65 | Epoch AI Benchmarking Hub | |
| Arena Maths | 1273#252 | Arena (LMArena) |
Knowledge
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| MMLUnot in index | 82.4%#13 | Epoch AI Benchmarking Hub |
Instruction following
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Instruction Followingnot in index | 1243#286 | Arena (LMArena) |
Human preference
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Arena Text | 1262#283 | Arena (LMArena) | |
| Arena Creative Writingnot in index | 1223#280 | Arena (LMArena) | |
| Arena Multi-turnnot in index | 1244#280 | Arena (LMArena) | |
| Arena Longer Queriesnot in index | 1262#285 | Arena (LMArena) |
Composite
| Benchmark | not stated | Source | Trend |
|---|---|---|---|
| Epoch Capabilities Indexnot in index | 125.3#163 | Epoch AI Benchmarking Hub | |
| AA Intelligence Index v4.3.2 | 6.3#535 | Artificial Analysis |
More from Alibaba
See also
Questions people ask
- What are Qwen2-72B's benchmark scores?
- As of 25 Oct 2026, Qwen2-72B scores 40.9 ±4.3 on the BenchLeader Index, strongest in maths (43) and weakest in coding (32). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
- How does Qwen2-72B rank?
- Qwen2-72B is #648 of 785 ranked configurations on 25 Oct 2026. 278 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
- When was Qwen2-72B released?
- Alibaba released Qwen2-72B on 7 Jun 2024.
Data as of 25 Oct 2026. Compare with another model.
Cite as: BenchLeader, “Qwen2-72B: benchmarks, pricing, speed and rank”, data as of 25 Oct 2026, https://www.benchleader.com/models/qwen2-72b.