Model comparison
Qwen3.8 Max vs StarCoder 2 15B
Qwen3.8 Max has enough public results to be ranked (#21); StarCoder 2 15B does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
Alibaba (Qwen)
NVIDIASummary
- They share 1 benchmark with published results for both. Qwen3.8 Max scores higher in 1 category and StarCoder 2 15B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where Qwen3.8 Max leads 52.3 to 36.0.
- StarCoder 2 15B has downloadable open weights; the other is API-only.
Side by side
| Qwen3.8 Max | StarCoder 2 15B | |
|---|---|---|
| Provider | Alibaba (Qwen) | NVIDIA |
| Noometry Index | 56.0 | 37.5 |
| Released | 2026-08-02 | 2024-02-20 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 131K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 38 | 7 |
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), StarCoder 2 15B: 36.0
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| DeepSWE | 57.5% | — |
| LMArena WebDev | 1671 | — |
| FrontierSWE | 15.8% | — |
| SciCode | 52.9% | — |
| LMArena Coding | 1499 | — |
| BigCodeBench Complete | — | 38.4% |
| HumanEval+ | — | 37.8% |
Agentic & Tool Use Not comparable
Qwen3.8 Max: 42.6 (#17), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| τ²-bench Banking | 55.1% | — |
| GDP.pdf | 23.2% | — |
Reasoning Not comparable
Qwen3.8 Max: 53.4 (#26), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| Epoch Capabilities Index | 156.69 | 104.61 |
| NYT Connections (extended) | 88.3% | — |
| CritPt | 20% | — |
| Chess Puzzles | 40% | — |
| LMArena Hard Prompts | 1493 | — |
| Mystery Game Puzzles | 38% | — |
| DTBench | 92% | — |
| LMCA | 46.2% | — |
| WinoGrande | — | 64.3% |
Math Not comparable
Qwen3.8 Max: 73.1 (#15), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74.7% | — |
| FrontierMath Tier 4 | 46.3% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 58% | — |
| LMArena Math | 1498 | — |
| GSM8K | — | 57.7% |
Knowledge Not comparable
Qwen3.8 Max: 61.7 (#25), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 47.3% | — |
| LMArena Expert | 1504 | — |
| ARC (AI2) Challenge | — | 47.2% |
| MMLU | — | 64.1% |
Multimodal Not comparable
Qwen3.8 Max: 36.9 (#70), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| LMArena Vision | 1314 | — |
| Furniture Assembly | 20% | — |
Multilingual Not comparable
Qwen3.8 Max: 56.6 (#18), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| LMArena Non-English | 1468 | — |
| LMArena Chinese | 1537 | — |
| LMArena French | 1502 | — |
| LMArena German | 1489 | — |
| LMArena Japanese | 1466 | — |
| LMArena Korean | 1467 | — |
| LMArena Russian | 1478 | — |
| LMArena Spanish | 1495 | — |
Instruction Following Not comparable
Qwen3.8 Max: 77.7 (#19), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| LMArena Instruction Following | 1478 | — |
Long Context Not comparable
Qwen3.8 Max: 45.5 (#30), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| LMArena Longer Query | 1486 | — |
Writing & Preference Not comparable
Qwen3.8 Max: 67.0 (#31), StarCoder 2 15B: —
| Benchmark | Qwen3.8 Max | StarCoder 2 15B |
|---|---|---|
| LMArena Text | 1480 | — |
| LMArena Creative Writing | 1478 | — |
| LMArena Multi-Turn | 1487 | — |
Frequently asked questions
Is Qwen3.8 Max better than StarCoder 2 15B?
Qwen3.8 Max has enough public results to be ranked (#21); StarCoder 2 15B does not yet, so treat this comparison as directional.
Is Qwen3.8 Max or StarCoder 2 15B better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 52.3 versus 36.0 in the Noometry coding category.
How many benchmarks do Qwen3.8 Max and StarCoder 2 15B share?
1 benchmark has published results for both models. Qwen3.8 Max has 38 scored results on Noometry and StarCoder 2 15B has 7.