Model comparison
Inkling vs Qwen2.5-Max
Inkling is the stronger model overall, scoring 44.1 to 40.7 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 6 categories and Qwen2.5-Max in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.1 to 35.3.
- Inkling has downloadable open weights; the other is API-only.
Side by side
| Inkling | Qwen2.5-Max | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 40.7 |
| Released | 2026-07-15 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 66K | — |
| Max output | 66K | — |
| Input $ / M tokens | $1.87 | — |
| Output $ / M tokens | $4.68 | — |
| Results tracked | 41 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5-Max leads
Inkling: 34.5 (#234), Qwen2.5-Max: 41.8 (#117)
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1464 | 1359 |
| FrontierCode | 14% | — |
| LMArena WebDev | 1413 | — |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| WeirdML | 32.3% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 946 | — |
Agentic & Tool Use Not comparable
Inkling: 29.6 (#85), Qwen2.5-Max: —
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.4 (#56), Qwen2.5-Max: 25.6 (#147)
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1360 |
| Epoch Capabilities Index | 148.54 | 132.53 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 87.5% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 37.6% | — |
| LiveBench | — | 62.3% |
Math Qwen2.5-Max leads
Inkling: 31.3 (#225), Qwen2.5-Max: 36.9 (#162)
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1479 | 1369 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
| LiveBench Math | — | 58.4% |
Knowledge Inkling leads
Inkling: 55.1 (#49), Qwen2.5-Max: 35.3 (#186)
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1465 | 1337 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
| Confabulations | — | 21.8% |
Multilingual Inkling leads
Inkling: 54.0 (#52), Qwen2.5-Max: 48.1 (#146)
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1434 | 1352 |
| LMArena Chinese | 1490 | 1382 |
| LMArena French | 1458 | 1396 |
| LMArena German | 1446 | 1350 |
| LMArena Japanese | 1429 | 1300 |
| LMArena Korean | 1404 | 1304 |
| LMArena Russian | 1429 | 1353 |
| LMArena Spanish | 1448 | 1377 |
Instruction Following Inkling leads
Inkling: 75.1 (#71), Qwen2.5-Max: 71.3 (#152)
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1426 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context Inkling leads
Inkling: 43.8 (#86), Qwen2.5-Max: 41.4 (#142)
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1434 | 1358 |
Writing & Preference Inkling leads
Inkling: 65.2 (#51), Qwen2.5-Max: 55.4 (#146)
| Benchmark | Inkling | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1441 | 1367 |
| LMArena Creative Writing | 1387 | 1339 |
| LMArena Multi-Turn | 1436 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is Inkling better than Qwen2.5-Max?
Inkling is the stronger model overall, scoring 44.1 to 40.7 on the Noometry Index.
Is Inkling or Qwen2.5-Max better for coding?
Qwen2.5-Max scores higher on coding benchmarks: 41.8 versus 34.5 in the Noometry coding category.
How many benchmarks do Inkling and Qwen2.5-Max share?
18 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen2.5-Max has 27.