Model comparison
GPT-6 Sol vs Qwen3 Max
GPT-6 Sol is the stronger model overall, scoring 49.2 to 43.5 on the Noometry Index. Qwen3 Max costs 1.7× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. GPT-6 Sol scores higher in 4 categories and Qwen3 Max in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 22.0.
- The biggest single-benchmark swing is NYT Connections (extended): 90.1% for GPT-6 Sol and 30.1% for Qwen3 Max.
- Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $2 / $10 for GPT-6 Sol.
- GPT-6 Sol accepts more context: 1.05M tokens versus 262K.
Side by side
| GPT-6 Sol | Qwen3 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 49.2 | 43.5 |
| Released | 2026-09-22 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 1.05M | 262K |
| Max output | 128K | 66K |
| Input $ / M tokens | $2 | $1.20 |
| Output $ / M tokens | $10 | $6 |
| Results tracked | 22 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 59.6 (#11), Qwen3 Max: 42.4 (#93)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1453 | 1456 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1692 | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
GPT-6 Sol: 33.5 (#49), Qwen3 Max: —
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| GDP.pdf | 28% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 49.3 (#34), Qwen3 Max: 22.0 (#186)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 90.1% | 30.1% |
| LMArena Hard Prompts | 1420 | 1448 |
| Kagi LLM Benchmark | — | 72.5% |
| Chess Puzzles | — | 4% |
| EBR-Bench | 53.3% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |
| Epoch Capabilities Index | — | 142.41 |
Math Qwen3 Max leads
GPT-6 Sol: 35.8 (#135), Qwen3 Max: 37.6 (#94)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Math | 1404 | 1447 |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| MATH Level 5 | — | 97.1% |
Knowledge Qwen3 Max leads
GPT-6 Sol: 43.0 (#87), Qwen3 Max: 48.1 (#72)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Expert | 1449 | 1457 |
| GPQA Diamond | — | 72.6% |
| SimpleQA Verified | — | 48.7% |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#9), Qwen3 Max: —
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| Furniture Assembly | 58.3% | — |
Multilingual Qwen3 Max leads
GPT-6 Sol: 51.0 (#113), Qwen3 Max: 53.9 (#58)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1389 | 1429 |
| LMArena Chinese | 1416 | 1479 |
| LMArena Russian | 1407 | 1428 |
| LMArena Spanish | 1377 | 1463 |
| LMArena French | — | 1450 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1397 |
Instruction Following Too close to call
GPT-6 Sol: 74.4 (#97), Qwen3 Max: 75.0 (#81)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1406 | 1420 |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.2 (#100), Qwen3 Max: 41.6 (#129)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1415 | 1439 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 72.3 (#15), Qwen3 Max: 62.6 (#72)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Text | 1396 | 1439 |
| LMArena Creative Writing | 1392 | 1401 |
| LMArena Multi-Turn | 1405 | 1446 |
| EQ-Bench Creative Writing | 2125 | — |
Frequently asked questions
Is GPT-6 Sol better than Qwen3 Max?
GPT-6 Sol is the stronger model overall, scoring 49.2 to 43.5 on the Noometry Index. Qwen3 Max costs 1.7× less per token, which makes it the better buy when GPT-6 Sol's lead doesn't matter for your workload.
Which is cheaper, GPT-6 Sol or Qwen3 Max?
Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; GPT-6 Sol lists at $2 and $10.
Is GPT-6 Sol or Qwen3 Max better for coding?
GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 262K.
How many benchmarks do GPT-6 Sol and Qwen3 Max share?
14 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and Qwen3 Max has 33.