Model comparison
GPT-5.2 Pro vs Qwen2.5 72B Instruct
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 31.5 on the Noometry Index. Qwen2.5 72B Instruct costs 24× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. GPT-5.2 Pro scores higher in 2 categories and Qwen2.5 72B Instruct in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 Pro leads 64.8 to 18.1.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-5.2 Pro accepts more context: 400K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.2 Pro | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 52.2 | 31.5 |
| Released | 2025-12-11 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $21 | $1.40 |
| Output $ / M tokens | $168 | $5.60 |
| Results tracked | 8 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| LMArena Coding | — | 1293 |
| BigCodeBench Complete | — | 55.9% |
Agentic & Tool Use Not comparable
GPT-5.2 Pro: —, Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.8 (#31), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| Epoch Capabilities Index | 155.41 | 129.01 |
| ARC-AGI-2 | 54.2% | — |
| SimpleBench | 57.4% | — |
| NYT Connections (extended) | 79.3% | — |
| ARC-AGI-1 | 90.5% | — |
| LMArena Hard Prompts | — | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 64.8 (#23), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | — |
| FrontierMath Tier 4 | 46% | — |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| LMArena Math | — | 1283 |
| MATH Level 5 | — | 63.2% |
| FrontierMath Tier 4 (v1) | 31.3% | — |
Knowledge Not comparable
GPT-5.2 Pro: —, Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| LMArena Expert | — | 1245 |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multilingual Not comparable
GPT-5.2 Pro: —, Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | — | 1252 |
| LMArena Chinese | — | 1272 |
| LMArena French | — | 1279 |
| LMArena German | — | 1234 |
| LMArena Japanese | — | 1180 |
| LMArena Korean | — | 1188 |
| LMArena Russian | — | 1264 |
| LMArena Spanish | — | 1255 |
Instruction Following Not comparable
GPT-5.2 Pro: —, Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | — | 80.6% |
| LMArena Instruction Following | — | 1254 |
Long Context Not comparable
GPT-5.2 Pro: —, Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | — | 1282 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | GPT-5.2 Pro | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | — | 1269 |
| LMArena Creative Writing | — | 1221 |
| WildBench | — | 80.2% |
| LMArena Multi-Turn | — | 1272 |
Frequently asked questions
Is GPT-5.2 Pro better than Qwen2.5 72B Instruct?
GPT-5.2 Pro is the stronger model overall, scoring 52.2 to 31.5 on the Noometry Index. Qwen2.5 72B Instruct costs 24× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 Pro or Qwen2.5 72B Instruct?
Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; GPT-5.2 Pro lists at $21 and $168.
Which has the bigger context window?
GPT-5.2 Pro does, with 400K tokens against 131K.
How many benchmarks do GPT-5.2 Pro and Qwen2.5 72B Instruct share?
1 benchmark has published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and Qwen2.5 72B Instruct has 43.