Model comparison
Inkling vs Qwen-14B
Inkling is the stronger model overall, scoring 44.1 to 31.4 on the Noometry Index.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Inkling scores higher in 7 categories and Qwen-14B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Inkling leads 65.2 to 27.6.
Side by side
| Inkling | Qwen-14B | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 31.4 |
| Released | 2026-07-15 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 66K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.87 | — |
| Output $ / M tokens | $4.68 | — |
| Results tracked | 41 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Inkling leads
Inkling: 34.5 (#234), Qwen-14B: 31.2 (#288)
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| LMArena Coding | 1464 | 1071 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Qwen-14B: —
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Qwen-14B: 19.6 (#257)
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1027 |
| Epoch Capabilities Index | 148.54 | 113.03 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| BIG-Bench Hard | — | 55% |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math Too close to call
Inkling: 31.3 (#225), Qwen-14B: 31.2 (#227)
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| LMArena Math | 1479 | 1068 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| GSM8K | — | 61.3% |
Knowledge Not comparable
Inkling: 55.1 (#49), Qwen-14B: —
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| LMArena Expert | 1465 | — |
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual Inkling leads
Inkling: 54.0 (#52), Qwen-14B: 27.5 (#275)
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1434 | 1041 |
| LMArena Chinese | 1490 | 1077 |
| LMArena French | 1458 | — |
| LMArena German | 1446 | — |
| LMArena Japanese | 1429 | — |
| LMArena Korean | 1404 | — |
| LMArena Russian | 1429 | — |
| LMArena Spanish | 1448 | — |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Qwen-14B: 52.4 (#289)
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1426 | 1031 |
Long Context Inkling leads
Inkling: 43.8 (#86), Qwen-14B: 31.3 (#280)
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1434 | 1028 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Qwen-14B: 27.6 (#299)
| Benchmark | Inkling | Qwen-14B |
|---|---|---|
| LMArena Text | 1441 | 1051 |
| LMArena Creative Writing | 1387 | 1028 |
| LMArena Multi-Turn | 1436 | 1022 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Qwen-14B?
Inkling is the stronger model overall, scoring 44.1 to 31.4 on the Noometry Index.
Is Inkling or Qwen-14B better for coding?
Inkling scores higher on coding benchmarks: 34.5 versus 31.2 in the Noometry coding category.
How many benchmarks do Inkling and Qwen-14B share?
11 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen-14B has 18.