Model comparison
Qwen2.5 72B Instruct vs Ring-2.6-1T
Qwen2.5 72B Instruct has enough public results to be ranked (#259); 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 32.8.
Side by side
| Qwen2.5 72B Instruct | Ring-2.6-1T | |
|---|---|---|
| Provider | Alibaba (Qwen) | Ant Group (inclusionAI) |
| Noometry Index | 31.5 | 36.3 |
| Released | 2024-09 | 2026-05-14 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 8K | — |
| Input $ / M tokens | $1.40 | — |
| Output $ / M tokens | $5.60 | — |
| Results tracked | 43 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Ring-2.6-1T leads
Qwen2.5 72B Instruct: 32.8 (#256), Ring-2.6-1T: 40.1
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| SciCode | — | 42.4% |
| WeirdML | 16% | — |
| BigCodeBench Instruct | 45.8% | — |
| LMArena Coding | 1293 | — |
| BigCodeBench Complete | 55.9% | — |
| ALE-Bench | — | 432.57 |
Agentic & Tool Use Not comparable
Qwen2.5 72B Instruct: 22.0 (#124), Ring-2.6-1T: —
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| TheAgentCompany | 5.7% | — |
| BALROG | 16.2% | — |
| METR Time Horizons | 35.8% | — |
Reasoning Ring-2.6-1T leads
Qwen2.5 72B Instruct: 21.4 (#197), Ring-2.6-1T: 25.3
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| CritPt | — | 3.7% |
| LMArena Hard Prompts | 1271 | — |
| DTBench | 62.9% | — |
| LMCA | 13.4% | — |
| BIG-Bench Hard | 79.8% | — |
| Epoch Capabilities Index | 129.01 | — |
| ForecastBench | 57.5 | — |
| HellaSwag | 84.8% | — |
| PIQA | 82.6% | — |
| WinoGrande | 82.3% | — |
Math Not comparable
Qwen2.5 72B Instruct: 18.1 (#281), Ring-2.6-1T: —
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.1% | — |
| Omni-MATH | 33% | — |
| LMArena Math | 1283 | — |
| MATH Level 5 | 63.2% | — |
Knowledge Not comparable
Qwen2.5 72B Instruct: 26.9 (#247), Ring-2.6-1T: —
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| 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
Qwen2.5 72B Instruct: 41.2 (#208), Ring-2.6-1T: —
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| 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
Qwen2.5 72B Instruct: 65.7 (#216), Ring-2.6-1T: —
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| IFEval | 80.6% | — |
| LMArena Instruction Following | 1254 | — |
Long Context Not comparable
Qwen2.5 72B Instruct: 38.9 (#183), Ring-2.6-1T: —
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| LMArena Longer Query | 1282 | — |
Writing & Preference Not comparable
Qwen2.5 72B Instruct: 46.9 (#210), Ring-2.6-1T: —
| Benchmark | Qwen2.5 72B Instruct | Ring-2.6-1T |
|---|---|---|
| LMArena Text | 1269 | — |
| LMArena Creative Writing | 1221 | — |
| WildBench | 80.2% | — |
| LMArena Multi-Turn | 1272 | — |
Frequently asked questions
Is Qwen2.5 72B Instruct better than Ring-2.6-1T?
Qwen2.5 72B Instruct has enough public results to be ranked (#259); Ring-2.6-1T does not yet, so treat this comparison as directional.
Is Qwen2.5 72B Instruct or Ring-2.6-1T better for coding?
Ring-2.6-1T scores higher on coding benchmarks: 40.1 versus 32.8 in the Noometry coding category.
How many benchmarks do Qwen2.5 72B Instruct and Ring-2.6-1T share?
0 benchmarks have published results for both models. Qwen2.5 72B Instruct has 43 scored results on Noometry and Ring-2.6-1T has 3.