Model comparison
Inkling vs Qwen3-Coder 480B-A35B Instruct
Inkling is the stronger model overall, scoring 44.1 to 37.7 on the Noometry Index.
Last verified . 20 shared benchmarks.
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. Inkling scores higher in 7 categories and Qwen3-Coder 480B-A35B Instruct in 2 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Inkling leads 55.2 to 36.4.
- The biggest single-benchmark swing is WeirdML: 32.3% for Inkling and 41.2% for Qwen3-Coder 480B-A35B Instruct.
- Inkling is cheaper at $1.87 / $4.68 per million input/output tokens, against $1.50 / $7.50 for Qwen3-Coder 480B-A35B Instruct.
- Qwen3-Coder 480B-A35B Instruct accepts more context: 262K tokens versus 66K.
Side by side
| Inkling | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Thinking Machines Lab | Alibaba (Qwen) |
| Noometry Index | 44.1 | 37.7 |
| Released | 2026-07-15 | 2025-04 |
| Weights | Open | Open |
| Context window | 66K | 262K |
| Max output | 66K | 66K |
| Input $ / M tokens | $1.87 | $1.50 |
| Output $ / M tokens | $4.68 | $7.50 |
| Results tracked | 41 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3-Coder 480B-A35B Instruct leads
Inkling: 34.1 (#229), Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1412 | 1275 |
| WeirdML | 32.3% | 41.2% |
| LMArena Coding | 1463 | 1413 |
| ALE-Bench | 946 | 461.45 |
| FrontierCode | 14% | — |
| SWE-bench Verified (bash only) | — | 55.4% |
| FrontierSWE | 4.1% | — |
| SciCode | 47% | — |
| GSO | — | 4.9% |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Inkling leads
Inkling: 29.5 (#76), Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| APEX-Agents | 33.8% | — |
| τ²-bench Banking | 25% | — |
Reasoning Inkling leads
Inkling: 40.6 (#48), Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1452 | 1372 |
| ARC-AGI-2 | 36.5% | — |
| SimpleBench | 50% | — |
| Kagi LLM Benchmark | — | 49.5% |
| ARC-AGI-1 | 79.5% | — |
| CritPt | 5.4% | — |
| Chess Puzzles | 21% | — |
| DTBench | 87.5% | — |
| LMCA | 37.6% | — |
| Epoch Capabilities Index | 148.6 | — |
Math Qwen3-Coder 480B-A35B Instruct leads
Inkling: 31.2 (#198), Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1482 | 1364 |
| FrontierMath (Tiers 1-3) | 33.3% | — |
| FrontierMath Tier 4 | 4.9% | — |
| OTIS Mock AIME 2024-2025 | 88.9% | — |
| ProofBench | 0% | — |
Knowledge Inkling leads
Inkling: 55.2 (#44), Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1468 | 1337 |
| GPQA Diamond | 88.3% | — |
| SimpleQA Verified | 40.3% | — |
Multilingual Inkling leads
Inkling: 54.2 (#49), Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1434 | 1345 |
| LMArena Chinese | 1495 | 1356 |
| LMArena French | 1453 | 1394 |
| LMArena German | 1456 | 1324 |
| LMArena Japanese | 1428 | 1309 |
| LMArena Korean | 1401 | 1307 |
| LMArena Russian | 1430 | 1367 |
| LMArena Spanish | 1442 | 1360 |
Instruction Following Inkling leads
Inkling: 75.3 (#65), Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1427 | 1356 |
Long Context Inkling leads
Inkling: 43.9 (#79), Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1436 | 1379 |
Writing & Preference Inkling leads
Inkling: 65.5 (#48), Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)
| Benchmark | Inkling | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1443 | 1356 |
| LMArena Creative Writing | 1390 | 1333 |
| LMArena Multi-Turn | 1436 | 1365 |
| EQ-Bench Creative Writing | 1611 | — |
| EQ-Bench 4 | 1226 | — |
Frequently asked questions
Is Inkling better than Qwen3-Coder 480B-A35B Instruct?
Inkling is the stronger model overall, scoring 44.1 to 37.7 on the Noometry Index.
Which is cheaper, Inkling or Qwen3-Coder 480B-A35B Instruct?
Inkling is cheaper. It lists at $1.87 per million input tokens and $4.68 per million output tokens; Qwen3-Coder 480B-A35B Instruct lists at $1.50 and $7.50.
Is Inkling or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3-Coder 480B-A35B Instruct scores higher on coding benchmarks: 36.2 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3-Coder 480B-A35B Instruct does, with 262K tokens against 66K.
How many benchmarks do Inkling and Qwen3-Coder 480B-A35B Instruct share?
20 benchmarks have published results for both models. Inkling has 41 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.