Model comparison
Qwen3.8 Max vs Qwen3-Coder 480B-A35B Instruct
Qwen3.8 Max is the stronger model overall, scoring 56.0 to 37.7 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Qwen3.8 Max scores higher in 9 categories and Qwen3-Coder 480B-A35B Instruct in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.1 to 34.9.
- Both cost about the same: $2 input and $6 output per million tokens.
- Qwen3.8 Max accepts more context: 1M tokens versus 262K.
- Qwen3-Coder 480B-A35B Instruct has downloadable open weights; the other is API-only.
Side by side
| Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 56.0 | 37.7 |
| Released | 2026-08-02 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 131K | 66K |
| Input $ / M tokens | $2 | $1.50 |
| Output $ / M tokens | $6 | $7.50 |
| Results tracked | 38 | 25 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Qwen3.8 Max: 52.3 (#30), Qwen3-Coder 480B-A35B Instruct: 36.2 (#199)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena WebDev | 1671 | 1275 |
| LMArena Coding | 1499 | 1413 |
| DeepSWE | 57.5% | — |
| SWE-bench Verified (bash only) | — | 55.4% |
| FrontierSWE | 15.8% | — |
| SciCode | 52.9% | — |
| GSO | — | 4.9% |
| WeirdML | — | 41.2% |
| ALE-Bench | — | 461.45 |
| AlgoTune | — | 1.44 |
Agentic & Tool Use Qwen3.8 Max leads
Qwen3.8 Max: 42.6 (#17), Qwen3-Coder 480B-A35B Instruct: 23.7 (#116)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| Terminal-Bench | — | 27.2% |
| τ²-bench Banking | 55.1% | — |
| GDP.pdf | 23.2% | — |
Reasoning Qwen3.8 Max leads
Qwen3.8 Max: 53.4 (#26), Qwen3-Coder 480B-A35B Instruct: 24.7 (#141)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1493 | 1372 |
| Kagi LLM Benchmark | — | 49.5% |
| NYT Connections (extended) | 88.3% | — |
| CritPt | 20% | — |
| Chess Puzzles | 40% | — |
| Mystery Game Puzzles | 38% | — |
| DTBench | 92% | — |
| LMCA | 46.2% | — |
| Epoch Capabilities Index | 156.69 | — |
Math Qwen3.8 Max leads
Qwen3.8 Max: 73.1 (#15), Qwen3-Coder 480B-A35B Instruct: 34.9 (#151)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Math | 1498 | 1364 |
| FrontierMath (Tiers 1-3) | 74.7% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 58% | — |
Knowledge Qwen3.8 Max leads
Qwen3.8 Max: 61.7 (#25), Qwen3-Coder 480B-A35B Instruct: 36.4 (#159)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Expert | 1504 | 1337 |
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 47.3% | — |
Multimodal Not comparable
Qwen3.8 Max: 36.9 (#70), Qwen3-Coder 480B-A35B Instruct: —
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 20% | — |
Multilingual Qwen3.8 Max leads
Qwen3.8 Max: 56.6 (#18), Qwen3-Coder 480B-A35B Instruct: 47.8 (#143)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Non-English | 1468 | 1345 |
| LMArena Chinese | 1537 | 1356 |
| LMArena French | 1502 | 1394 |
| LMArena German | 1489 | 1324 |
| LMArena Japanese | 1466 | 1309 |
| LMArena Korean | 1467 | 1307 |
| LMArena Russian | 1478 | 1367 |
| LMArena Spanish | 1495 | 1360 |
Instruction Following Qwen3.8 Max leads
Qwen3.8 Max: 77.7 (#19), Qwen3-Coder 480B-A35B Instruct: 71.8 (#142)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Instruction Following | 1478 | 1356 |
Long Context Qwen3.8 Max leads
Qwen3.8 Max: 45.5 (#30), Qwen3-Coder 480B-A35B Instruct: 42.0 (#126)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Longer Query | 1486 | 1379 |
Writing & Preference Qwen3.8 Max leads
Qwen3.8 Max: 67.0 (#31), Qwen3-Coder 480B-A35B Instruct: 55.5 (#142)
| Benchmark | Qwen3.8 Max | Qwen3-Coder 480B-A35B Instruct |
|---|---|---|
| LMArena Text | 1480 | 1356 |
| LMArena Creative Writing | 1478 | 1333 |
| LMArena Multi-Turn | 1487 | 1365 |
Frequently asked questions
Is Qwen3.8 Max better than Qwen3-Coder 480B-A35B Instruct?
Qwen3.8 Max is the stronger model overall, scoring 56.0 to 37.7 on the Noometry Index.
Which is cheaper, Qwen3.8 Max or Qwen3-Coder 480B-A35B Instruct?
Qwen3-Coder 480B-A35B Instruct is cheaper. It lists at $1.50 per million input tokens and $7.50 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Qwen3.8 Max or Qwen3-Coder 480B-A35B Instruct better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 36.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 262K.
How many benchmarks do Qwen3.8 Max and Qwen3-Coder 480B-A35B Instruct share?
18 benchmarks have published results for both models. Qwen3.8 Max has 38 scored results on Noometry and Qwen3-Coder 480B-A35B Instruct has 25.