Model comparison
Qwen1.5-72B vs Ring-2.6-1T
Qwen1.5-72B has enough public results to be ranked (#282); Ring-2.6-1T does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
Alibaba (Qwen)
Ant Group (inclusionAI)Summary
- The widest gap is in coding, where Ring-2.6-1T leads 40.1 to 31.4.
Side by side
| Qwen1.5-72B | Ring-2.6-1T | |
|---|---|---|
| Provider | Alibaba (Qwen) | Ant Group (inclusionAI) |
| Noometry Index | 30.3 | 36.3 |
| Released | 2024-02-04 | 2026-05-14 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ring-2.6-1T leads
Qwen1.5-72B: 31.4 (#272), Ring-2.6-1T: 40.1
| Benchmark | Qwen1.5-72B | Ring-2.6-1T |
|---|---|---|
| SciCode | — | 42.4% |
| BigCodeBench Instruct | 33.2% | — |
| LMArena Coding | 1166 | — |
| BigCodeBench Complete | 40.3% | — |
| ALE-Bench | — | 432.57 |
| HumanEval+ | 59.1% | — |
| MBPP+ | 61.6% | — |
Reasoning Ring-2.6-1T leads
Qwen1.5-72B: 21.2 (#201), Ring-2.6-1T: 25.3
| Benchmark | Qwen1.5-72B | Ring-2.6-1T |
|---|---|---|
| CritPt | — | 3.7% |
| LMArena Hard Prompts | 1148 | — |
Math Not comparable
Qwen1.5-72B: 30.7 (#205), Ring-2.6-1T: —
| Benchmark | Qwen1.5-72B | Ring-2.6-1T |
|---|---|---|
| LMArena Math | 1164 | — |
Knowledge Not comparable
Qwen1.5-72B: 11.5 (#295), Ring-2.6-1T: —
| Benchmark | Qwen1.5-72B | Ring-2.6-1T |
|---|---|---|
| GPQA Diamond | 28.8% | — |
| LMArena Expert | 1136 | — |
Multilingual Not comparable
Qwen1.5-72B: 33.4 (#248), Ring-2.6-1T: —
| Benchmark | Qwen1.5-72B | Ring-2.6-1T |
|---|---|---|
| LMArena Non-English | 1135 | — |
| LMArena Chinese | 1186 | — |
| LMArena French | 1158 | — |
| LMArena German | 1084 | — |
| LMArena Japanese | 1061 | — |
| LMArena Korean | 1049 | — |
| LMArena Russian | 1104 | — |
| LMArena Spanish | 1110 | — |
Instruction Following Not comparable
Qwen1.5-72B: 59.6 (#251), Ring-2.6-1T: —
| Benchmark | Qwen1.5-72B | Ring-2.6-1T |
|---|---|---|
| LMArena Instruction Following | 1142 | — |
Long Context Not comparable
Qwen1.5-72B: 35.0 (#238), Ring-2.6-1T: —
| Benchmark | Qwen1.5-72B | Ring-2.6-1T |
|---|---|---|
| LMArena Longer Query | 1157 | — |
Writing & Preference Not comparable
Qwen1.5-72B: 37.4 (#253), Ring-2.6-1T: —
| Benchmark | Qwen1.5-72B | Ring-2.6-1T |
|---|---|---|
| LMArena Text | 1166 | — |
| LMArena Creative Writing | 1137 | — |
| LMArena Multi-Turn | 1160 | — |
Frequently asked questions
Is Qwen1.5-72B better than Ring-2.6-1T?
Qwen1.5-72B has enough public results to be ranked (#282); Ring-2.6-1T does not yet, so treat this comparison as directional.
Is Qwen1.5-72B or Ring-2.6-1T better for coding?
Ring-2.6-1T scores higher on coding benchmarks: 40.1 versus 31.4 in the Noometry coding category.
How many benchmarks do Qwen1.5-72B and Ring-2.6-1T share?
0 benchmarks have published results for both models. Qwen1.5-72B has 22 scored results on Noometry and Ring-2.6-1T has 3.