Model comparison
GPT-5 Pro vs Qwen3 Max
GPT-5 Pro is the stronger model overall, scoring 46.2 to 43.5 on the Noometry Index. Qwen3 Max costs 17× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
Alibaba (Qwen)Summary
- They share 3 benchmarks with published results for both. GPT-5 Pro scores higher in 4 categories and Qwen3 Max in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5 Pro leads 39.2 to 22.0.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 55.8% for GPT-5 Pro and 18.9% for Qwen3 Max.
- Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $15 / $120 for GPT-5 Pro.
- GPT-5 Pro accepts more context: 400K tokens versus 262K.
Side by side
| GPT-5 Pro | Qwen3 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 46.2 | 43.5 |
| Released | 2025-10-06 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 262K |
| Max output | 272K | 66K |
| Input $ / M tokens | $15 | $1.20 |
| Output $ / M tokens | $120 | $6 |
| Results tracked | 12 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5 Pro leads
GPT-5 Pro: 43.4 (#77), Qwen3 Max: 42.4 (#93)
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| WeirdML | 60.4% | — |
| LMArena Coding | — | 1456 |
| ALE-Bench | — | 370.45 |
| AlgoTune | 1.31 | — |
Agentic & Tool Use Not comparable
GPT-5 Pro: —, Qwen3 Max: —
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | — | 71.56 |
Reasoning GPT-5 Pro leads
GPT-5 Pro: 39.2 (#52), Qwen3 Max: 22.0 (#186)
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 76.8% | 72.5% |
| Epoch Capabilities Index | 150.26 | 142.41 |
| ARC-AGI-2 | 18.3% | — |
| SimpleBench | 61.6% | — |
| NYT Connections (extended) | — | 30.1% |
| ARC-AGI-1 | 70.2% | — |
| Chess Puzzles | — | 4% |
| EnigmaEval | 18.8% | — |
| LMArena Hard Prompts | — | 1448 |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 82.1% |
| LMCA | — | 28.3% |
Math GPT-5 Pro leads
GPT-5 Pro: 48.0 (#53), Qwen3 Max: 37.6 (#94)
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 55.8% | 18.9% |
| FrontierMath Tier 4 | 19.5% | — |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LMArena Math | — | 1447 |
| MATH Level 5 | — | 97.1% |
| FrontierMath Tier 4 (v1) | 14.6% | — |
Knowledge GPT-5 Pro leads
GPT-5 Pro: 56.2 (#39), Qwen3 Max: 48.1 (#72)
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| GPQA Diamond | — | 72.6% |
| Humanity's Last Exam | 31.6% | — |
| SimpleQA Verified | — | 48.7% |
| LMArena Expert | — | 1457 |
Multilingual Not comparable
GPT-5 Pro: —, Qwen3 Max: 53.9 (#58)
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| LMArena Non-English | — | 1429 |
| LMArena Chinese | — | 1479 |
| LMArena French | — | 1450 |
| LMArena German | — | 1463 |
| LMArena Japanese | — | 1399 |
| LMArena Korean | — | 1397 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1463 |
Instruction Following Not comparable
GPT-5 Pro: —, Qwen3 Max: 75.0 (#81)
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | — | 1420 |
Long Context Not comparable
GPT-5 Pro: —, Qwen3 Max: 41.6 (#129)
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
| LMArena Longer Query | — | 1439 |
Writing & Preference Not comparable
GPT-5 Pro: —, Qwen3 Max: 62.6 (#72)
| Benchmark | GPT-5 Pro | Qwen3 Max |
|---|---|---|
| LMArena Text | — | 1439 |
| LMArena Creative Writing | — | 1401 |
| LMArena Multi-Turn | — | 1446 |
Frequently asked questions
Is GPT-5 Pro better than Qwen3 Max?
GPT-5 Pro is the stronger model overall, scoring 46.2 to 43.5 on the Noometry Index. Qwen3 Max costs 17× less per token, which makes it the better buy when GPT-5 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5 Pro or Qwen3 Max?
Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; GPT-5 Pro lists at $15 and $120.
Is GPT-5 Pro or Qwen3 Max better for coding?
GPT-5 Pro scores higher on coding benchmarks: 43.4 versus 42.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5 Pro does, with 400K tokens against 262K.
How many benchmarks do GPT-5 Pro and Qwen3 Max share?
3 benchmarks have published results for both models. GPT-5 Pro has 12 scored results on Noometry and Qwen3 Max has 33.