Model comparison
GPT-5.1 vs Qwen2.5 72B Instruct
GPT-5.1 is the stronger model overall, scoring 48.8 to 31.5 on the Noometry Index.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. GPT-5.1 scores higher in 9 categories and Qwen2.5 72B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.1 leads 50.3 to 18.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.6% for GPT-5.1 and 8.1% for Qwen2.5 72B Instruct.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $1.25 / $10 for GPT-5.1.
- GPT-5.1 accepts more context: 400K tokens versus 131K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1 | Qwen2.5 72B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 48.8 | 31.5 |
| Released | 2025-11-13 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $1.25 | $1.40 |
| Output $ / M tokens | $10 | $5.60 |
| Results tracked | 63 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.9 (#59), Qwen2.5 72B Instruct: 32.8 (#256)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 60.8% | 16% |
| LMArena Coding | 1454 | 1293 |
| SWE-bench Verified | 68% | — |
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| GSO | 13.7% | — |
| BigCodeBench Instruct | — | 45.8% |
| LiveBench Coding | 72.5% | — |
| BigCodeBench Complete | — | 55.9% |
| ALE-Bench | 1,192 | — |
Agentic & Tool Use GPT-5.1 leads
GPT-5.1: 32.5 (#55), Qwen2.5 72B Instruct: 22.0 (#124)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| TheAgentCompany | — | 5.7% |
| DeepResearch Bench | 42.8% | — |
| BALROG | — | 16.2% |
| LMArena Search | 1199 | — |
| METR Time Horizons | — | 35.8% |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.9 (#50), Qwen2.5 72B Instruct: 21.4 (#197)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1271 |
| DTBench | 90.1% | 62.9% |
| LMCA | 43.9% | 13.4% |
| Epoch Capabilities Index | 149.66 | 129.01 |
| ForecastBench | 58.1 | 57.5 |
| ARC-AGI-2 | 17.6% | — |
| SimpleBench | 53.2% | — |
| ARC-AGI-1 | 72.8% | — |
| CritPt | 4.9% | — |
| Chess Puzzles | 32% | — |
| EnigmaEval | 11.2% | — |
| LiveBench Reasoning | 95.8% | — |
| Mystery Game Puzzles | 19% | — |
| LiveBench Data Analysis | 72.1% | — |
| BIG-Bench Hard | — | 79.8% |
| HellaSwag | — | 84.8% |
| LiveBench | 78.8% | — |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |
Math GPT-5.1 leads
GPT-5.1: 50.3 (#45), Qwen2.5 72B Instruct: 18.1 (#281)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.6% | 8.1% |
| Omni-MATH | 46.4% | 33% |
| LMArena Math | 1446 | 1283 |
| LiveBench Math | 94.5% | — |
| MATH Level 5 | — | 63.2% |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5.1 leads
GPT-5.1: 50.5 (#65), Qwen2.5 72B Instruct: 26.9 (#247)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 87.6% | 49.1% |
| MMLU-Pro | 57.9% | 63.1% |
| GPQA (HELM) | 44.2% | 42.6% |
| LMArena Expert | 1470 | 1245 |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| Confabulations | — | 19.1% |
| Vectara Hallucination Rate | 10.9% | — |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |
Multimodal Not comparable
GPT-5.1: 44.0 (#17), Qwen2.5 72B Instruct: —
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1250 | — |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 54.0 (#51), Qwen2.5 72B Instruct: 41.2 (#208)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1431 | 1252 |
| LMArena Chinese | 1495 | 1272 |
| LMArena French | 1451 | 1279 |
| LMArena German | 1439 | 1234 |
| LMArena Japanese | 1453 | 1180 |
| LMArena Korean | 1401 | 1188 |
| LMArena Russian | 1435 | 1264 |
| LMArena Spanish | 1430 | 1255 |
Instruction Following GPT-5.1 leads
GPT-5.1: 84.0 (#1), Qwen2.5 72B Instruct: 65.7 (#216)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | 93.5% | 80.6% |
| LMArena Instruction Following | 1442 | 1254 |
| LiveBench Instruction Following | 93.3% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Qwen2.5 72B Instruct: 38.9 (#183)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1448 | 1282 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.7 (#53), Qwen2.5 72B Instruct: 46.9 (#210)
| Benchmark | GPT-5.1 | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1443 | 1269 |
| LMArena Creative Writing | 1427 | 1221 |
| WildBench | 86.3% | 80.2% |
| LMArena Multi-Turn | 1449 | 1272 |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Qwen2.5 72B Instruct?
GPT-5.1 is the stronger model overall, scoring 48.8 to 31.5 on the Noometry Index.
Which is cheaper, GPT-5.1 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-5.1 lists at $1.25 and $10.
Is GPT-5.1 or Qwen2.5 72B Instruct better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.9 versus 32.8 in the Noometry coding category.
Which has the bigger context window?
GPT-5.1 does, with 400K tokens against 131K.
How many benchmarks do GPT-5.1 and Qwen2.5 72B Instruct share?
29 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Qwen2.5 72B Instruct has 43.