Model comparison
GPT-5.1 vs Qwen2-72B
GPT-5.1 is the stronger model overall, scoring 49.0 to 30.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. GPT-5.1 scores higher in 9 categories and Qwen2-72B in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.1 leads 50.6 to 21.2.
- The biggest single-benchmark swing is WeirdML: 60.8% for GPT-5.1 and 11.3% for Qwen2-72B.
- Qwen2-72B has downloadable open weights; the other is API-only.
Side by side
| GPT-5.1 | Qwen2-72B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 49.0 | 30.0 |
| Released | 2025-11-13 | 2024-06-07 |
| Weights | Proprietary | Open |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 63 | 26 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.1 leads
GPT-5.1: 46.4 (#66), Qwen2-72B: 29.1 (#310)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| WeirdML | 60.8% | 11.3% |
| LMArena Coding | 1454 | 1196 |
| SWE-bench Verified | 68% | — |
| SWE-bench Verified (bash only) | 66% | — |
| LMArena WebDev | 1395 | — |
| SciCode | 43.3% | — |
| GSO | 13.7% | — |
| BigCodeBench Instruct | — | 38.5% |
| LiveBench Coding | 72.5% | — |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 1,192 | — |
Agentic & Tool Use GPT-5.1 leads
GPT-5.1: 32.7 (#60), Qwen2-72B: 17.0 (#146)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| Terminal-Bench | 47.6% | — |
| TheAgentCompany | — | 1.1% |
| DeepResearch Bench | 42.8% | — |
| LMArena Search | 1199 | — |
| METR Time Horizons | — | 29.9% |
| Vending-Bench 2 | 1,473 | — |
Reasoning GPT-5.1 leads
GPT-5.1: 39.8 (#58), Qwen2-72B: 23.2 (#181)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1457 | 1191 |
| Epoch Capabilities Index | 149.64 | 125.28 |
| 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% | — |
| DTBench | 90.1% | — |
| LiveBench Data Analysis | 72.1% | — |
| LMCA | 43.9% | — |
| ForecastBench | 58.1 | — |
| LiveBench | 78.8% | — |
Math GPT-5.1 leads
GPT-5.1: 52.2 (#51), Qwen2-72B: 30.2 (#236)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| LMArena Math | 1447 | 1235 |
| OTIS Mock AIME 2024-2025 | 88.6% | — |
| Omni-MATH | 46.4% | — |
| LiveBench Math | 94.5% | — |
| MATH Level 5 | — | 39.1% |
| FrontierMath (Feb 2025 set) | 31% | — |
| FrontierMath Tier 4 (v1) | 12.5% | — |
Knowledge GPT-5.1 leads
GPT-5.1: 50.6 (#71), Qwen2-72B: 21.2 (#275)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| GPQA Diamond | 87.6% | 40.8% |
| LMArena Expert | 1470 | 1171 |
| Humanity's Last Exam | 23.7% | — |
| SimpleQA Verified | 48% | — |
| MMLU-Pro | 57.9% | — |
| Vectara Hallucination Rate | 10.9% | — |
| GPQA (HELM) | 44.2% | — |
| MMLU | — | 82.4% |
Multimodal Not comparable
GPT-5.1: 44.8 (#19), Qwen2-72B: —
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| LMArena Vision | 1250 | — |
| VPCT | 58.7% | — |
| LMArena Document | 1403 | — |
Multilingual GPT-5.1 leads
GPT-5.1: 53.8 (#56), Qwen2-72B: 35.9 (#244)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1431 | 1176 |
| LMArena Chinese | 1495 | 1240 |
| LMArena French | 1450 | 1170 |
| LMArena German | 1438 | 1151 |
| LMArena Japanese | 1453 | 1111 |
| LMArena Korean | 1401 | 1083 |
| LMArena Russian | 1435 | 1169 |
| LMArena Spanish | 1433 | 1169 |
Instruction Following GPT-5.1 leads
GPT-5.1: 83.9 (#1), Qwen2-72B: 61.7 (#241)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1443 | 1181 |
| LiveBench Instruction Following | 93.3% | — |
| IFEval | 93.5% | — |
Long Context GPT-5.1 leads
GPT-5.1: 47.6 (#14), Qwen2-72B: 36.1 (#235)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1447 | 1192 |
| CL-bench | 23.7% | — |
| CL-bench Life | 17.3% | — |
Writing & Preference GPT-5.1 leads
GPT-5.1: 64.5 (#55), Qwen2-72B: 40.8 (#241)
| Benchmark | GPT-5.1 | Qwen2-72B |
|---|---|---|
| LMArena Text | 1443 | 1203 |
| LMArena Creative Writing | 1427 | 1181 |
| LMArena Multi-Turn | 1450 | 1196 |
| WildBench | 86.3% | — |
| LiveBench Language | 80.2% | — |
Frequently asked questions
Is GPT-5.1 better than Qwen2-72B?
GPT-5.1 is the stronger model overall, scoring 49.0 to 30.0 on the Noometry Index.
Is GPT-5.1 or Qwen2-72B better for coding?
GPT-5.1 scores higher on coding benchmarks: 46.4 versus 29.1 in the Noometry coding category.
How many benchmarks do GPT-5.1 and Qwen2-72B share?
20 benchmarks have published results for both models. GPT-5.1 has 63 scored results on Noometry and Qwen2-72B has 26.