Model comparison
GPT-6 Sol vs Qwen1.5-72B
GPT-6 Sol is the stronger model overall, scoring 49.2 to 30.3 on the Noometry Index.
Last verified . 13 shared benchmarks.
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. GPT-6 Sol scores higher in 8 categories and Qwen1.5-72B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-6 Sol leads 72.3 to 37.4.
- Qwen1.5-72B has downloadable open weights; the other is API-only.
Side by side
| GPT-6 Sol | Qwen1.5-72B | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 49.2 | 30.3 |
| Released | 2026-09-22 | 2024-02-04 |
| Weights | Proprietary | Open |
| Context window | 1.05M | — |
| Max output | 128K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $10 | — |
| Results tracked | 22 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 59.6 (#11), Qwen1.5-72B: 31.4 (#272)
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1453 | 1166 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1692 | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
GPT-6 Sol: 33.5 (#49), Qwen1.5-72B: —
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| GDP.pdf | 28% | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 49.3 (#34), Qwen1.5-72B: 21.2 (#201)
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1148 |
| NYT Connections (extended) | 90.1% | — |
| EBR-Bench | 53.3% | — |
Math GPT-6 Sol leads
GPT-6 Sol: 35.8 (#135), Qwen1.5-72B: 30.7 (#205)
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1404 | 1164 |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 43.0 (#87), Qwen1.5-72B: 11.5 (#295)
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| LMArena Expert | 1449 | 1136 |
| GPQA Diamond | — | 28.8% |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#9), Qwen1.5-72B: —
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| Furniture Assembly | 58.3% | — |
Multilingual GPT-6 Sol leads
GPT-6 Sol: 51.0 (#113), Qwen1.5-72B: 33.4 (#248)
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1389 | 1135 |
| LMArena Chinese | 1416 | 1186 |
| LMArena Russian | 1407 | 1104 |
| LMArena Spanish | 1377 | 1110 |
| LMArena French | — | 1158 |
| LMArena German | — | 1084 |
| LMArena Japanese | — | 1061 |
| LMArena Korean | — | 1049 |
Instruction Following GPT-6 Sol leads
GPT-6 Sol: 74.4 (#97), Qwen1.5-72B: 59.6 (#251)
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1406 | 1142 |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.2 (#100), Qwen1.5-72B: 35.0 (#238)
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1415 | 1157 |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 72.3 (#15), Qwen1.5-72B: 37.4 (#253)
| Benchmark | GPT-6 Sol | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1396 | 1166 |
| LMArena Creative Writing | 1392 | 1137 |
| LMArena Multi-Turn | 1405 | 1160 |
| EQ-Bench Creative Writing | 2125 | — |
Frequently asked questions
Is GPT-6 Sol better than Qwen1.5-72B?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 30.3 on the Noometry Index.
Is GPT-6 Sol or Qwen1.5-72B better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 31.4 in the Noometry coding category.
How many benchmarks do GPT-6 Sol and Qwen1.5-72B share?
13 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and Qwen1.5-72B has 22.