Model comparison
Inkling vs Qwen1.5-72B
Inkling is the stronger model overall, scoring 44.1 to 30.8 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Inkling scores higher in 7 categories and Qwen1.5-72B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 11.5.
- The biggest single-benchmark swing is GPQA Diamond: 88.3% for Inkling and 28.8% for Qwen1.5-72B.
Side by side
| Inkling | Qwen1.5-72B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 30.8 |
| Released | 2026-07-15 | 2024-02-04 |
| Weights | Open | Open |
| Context window | 66K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.87 | — |
| Output $ / M tokens | $4.68 | — |
| Results tracked | 41 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Inkling: 34.5 (#234), Qwen1.5-72B: 31.9 (#277)
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| LMArena Coding | 1464 | 1165 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| BigCodeBench Instruct | — | 33.2% |
| BigCodeBench Complete | — | 40.3% |
| ALE-Bench | 946 | — |
| HumanEval+ | — | 59.1% |
| MBPP+ | — | 61.6% |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Qwen1.5-72B: —
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Qwen1.5-72B: 22.2 (#203)
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1148 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.54 | — |
Math Qwen1.5-72B leads
Inkling: 31.3 (#225), Qwen1.5-72B: 33.2 (#205)
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1479 | 1164 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
Knowledge Inkling leads
Inkling: 55.1 (#49), Qwen1.5-72B: 11.5 (#300)
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 88.3% | 28.8% |
| LMArena Expert | 1465 | 1136 |
| SimpleQA Verified | 40.3% | — |
Multilingual Inkling leads
Inkling: 54.0 (#52), Qwen1.5-72B: 33.2 (#253)
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1434 | 1135 |
| LMArena Chinese | 1490 | 1186 |
| LMArena French | 1458 | 1159 |
| LMArena German | 1446 | 1084 |
| LMArena Japanese | 1429 | 1061 |
| LMArena Korean | 1404 | 1050 |
| LMArena Russian | 1429 | 1104 |
| LMArena Spanish | 1448 | 1110 |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Qwen1.5-72B: 59.3 (#256)
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1141 |
Long Context Inkling leads
Inkling: 43.8 (#86), Qwen1.5-72B: 35.1 (#243)
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1434 | 1157 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Qwen1.5-72B: 37.3 (#258)
| Benchmark | Inkling | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1441 | 1166 |
| LMArena Creative Writing | 1387 | 1137 |
| LMArena Multi-Turn | 1436 | 1160 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Qwen1.5-72B?
Inkling is the stronger model overall, scoring 44.1 to 30.8 on the Noometry Index.
Is Inkling or Qwen1.5-72B better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 31.9 in the Noometry coding category.
How many benchmarks do Inkling and Qwen1.5-72B share?
18 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen1.5-72B has 22.