Model comparison
GPT-6 Sol vs Qwen3 Max
GPT-6 Sol is the stronger model overall, scoring 61.8 to 43.7 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 . 28 shared benchmarks.
Alibaba (Qwen)Summary
- They share 28 benchmarks with published results for both. GPT-6 Sol scores higher in 6 categories and Qwen3 Max in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 74.0 to 22.6.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 89.8% for GPT-6 Sol and 18.9% 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 | 61.8 | 43.7 |
| 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 | 45 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-6 Sol leads
GPT-6 Sol: 60.1 (#11), Qwen3 Max: 43.0 (#93)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1447 | 1456 |
| ALE-Bench | 2,462 | 370.45 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1688 | — |
| SciCode | 57.6% | — |
Agentic & Tool Use Not comparable
GPT-6 Sol: 37.2 (#36), Qwen3 Max: —
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | 14,428 | 71.56 |
| APEX-Agents | 54.3% | — |
| GDP.pdf | 26.4% | — |
Reasoning GPT-6 Sol leads
GPT-6 Sol: 74.0 (#9), Qwen3 Max: 22.6 (#190)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| NYT Connections (extended) | 90.1% | 30.1% |
| LMArena Hard Prompts | 1418 | 1448 |
| Mystery Game Puzzles | 56% | 5% |
| DTBench | 97.3% | 82.1% |
| LMCA | 59.1% | 28.3% |
| Epoch Capabilities Index | 162.72 | 142.38 |
| ARC-AGI-2 | 89.6% | — |
| Kagi LLM Benchmark | — | 72.5% |
| ARC-AGI-1 | 95.5% | — |
| CritPt | 30.9% | — |
| Chess Puzzles | — | 4% |
| EBR-Bench | 53.3% | — |
Math GPT-6 Sol leads
GPT-6 Sol: 87.2 (#7), Qwen3 Max: 38.7 (#131)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 89.8% | 18.9% |
| OTIS Mock AIME 2024-2025 | 100% | 73.3% |
| LMArena Math | 1402 | 1446 |
| FrontierMath Tier 4 | 90% | — |
| ProofBench | 83% | — |
| MATH Level 5 | — | 97.1% |
Knowledge GPT-6 Sol leads
GPT-6 Sol: 64.8 (#15), Qwen3 Max: 48.1 (#78)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 94.3% | 72.6% |
| SimpleQA Verified | 60.7% | 48.7% |
| LMArena Expert | 1439 | 1455 |
| Vectara Hallucination Rate | 6.5% | — |
Multimodal Not comparable
GPT-6 Sol: 47.6 (#10), Qwen3 Max: —
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1245 | — |
| Blueprint-Bench 2 | 36.9% | — |
| Furniture Assembly | 58.3% | — |
Multilingual Qwen3 Max leads
GPT-6 Sol: 50.5 (#118), Qwen3 Max: 53.7 (#62)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1385 | 1429 |
| LMArena Chinese | 1405 | 1478 |
| LMArena French | 1410 | 1449 |
| LMArena German | 1390 | 1463 |
| LMArena Japanese | 1385 | 1397 |
| LMArena Korean | 1341 | 1399 |
| LMArena Russian | 1401 | 1428 |
| LMArena Spanish | 1384 | 1462 |
Instruction Following Too close to call
GPT-6 Sol: 74.5 (#94), Qwen3 Max: 74.8 (#87)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1412 | 1419 |
Long Context GPT-6 Sol leads
GPT-6 Sol: 43.1 (#108), Qwen3 Max: 41.6 (#134)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1411 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference GPT-6 Sol leads
GPT-6 Sol: 71.9 (#18), Qwen3 Max: 62.4 (#76)
| Benchmark | GPT-6 Sol | Qwen3 Max |
|---|---|---|
| LMArena Text | 1395 | 1439 |
| LMArena Creative Writing | 1378 | 1402 |
| LMArena Multi-Turn | 1412 | 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 61.8 to 43.7 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: 60.1 versus 43.0 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?
28 benchmarks have published results for both models. GPT-6 Sol has 45 scored results on Noometry and Qwen3 Max has 33.