Model comparison
GPT-4o mini vs Qwen3 Max
Qwen3 Max is the stronger model overall, scoring 43.7 to 25.5 on the Noometry Index. GPT-4o mini costs 9.1× less per token, which makes it the better buy when Qwen3 Max'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-4o mini scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 Max leads 48.1 to 17.7.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.9% for GPT-4o mini and 73.3% for Qwen3 Max.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 128K.
Side by side
| GPT-4o mini | Qwen3 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 25.5 | 43.7 |
| Released | 2024-07-18 | 2025-09-23 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.15 | $1.20 |
| Output $ / M tokens | $0.60 | $6 |
| Results tracked | 60 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 Max leads
GPT-4o mini: 22.0 (#335), Qwen3 Max: 43.0 (#93)
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1290 | 1456 |
| Aider Polyglot | 3.6% | — |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 370.45 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Qwen3 Max: —
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| BALROG | 17.4% | — |
| Vending-Bench 2 | — | 71.56 |
Reasoning Qwen3 Max leads
GPT-4o mini: 8.7 (#347), Qwen3 Max: 22.6 (#190)
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 28.8% | 72.5% |
| Chess Puzzles | 0% | 4% |
| LMArena Hard Prompts | 1267 | 1448 |
| Mystery Game Puzzles | 12% | 5% |
| DTBench | 54.4% | 82.1% |
| LMCA | 10.4% | 28.3% |
| Epoch Capabilities Index | 126.56 | 142.38 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| NYT Connections (extended) | — | 30.1% |
| LiveBench Reasoning | 32.8% | — |
| LiveBench Data Analysis | 50% | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Qwen3 Max leads
GPT-4o mini: 10.4 (#314), Qwen3 Max: 38.7 (#131)
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 18.9% |
| OTIS Mock AIME 2024-2025 | 6.9% | 73.3% |
| LMArena Math | 1267 | 1446 |
| MATH Level 5 | 52.6% | 97.1% |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| GSM8K | 91.3% | — |
Knowledge Qwen3 Max leads
GPT-4o mini: 17.7 (#284), Qwen3 Max: 48.1 (#78)
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 37.7% | 72.6% |
| SimpleQA Verified | 8.3% | 48.7% |
| LMArena Expert | 1235 | 1455 |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), Qwen3 Max: —
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Qwen3 Max leads
GPT-4o mini: 42.0 (#199), Qwen3 Max: 53.7 (#62)
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1266 | 1429 |
| LMArena Chinese | 1265 | 1478 |
| LMArena French | 1297 | 1449 |
| LMArena German | 1272 | 1463 |
| LMArena Japanese | 1216 | 1397 |
| LMArena Korean | 1195 | 1399 |
| LMArena Russian | 1275 | 1428 |
| LMArena Spanish | 1276 | 1462 |
Instruction Following Qwen3 Max leads
GPT-4o mini: 61.9 (#239), Qwen3 Max: 74.8 (#87)
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1258 | 1419 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Qwen3 Max leads
GPT-4o mini: 39.1 (#186), Qwen3 Max: 41.6 (#134)
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1289 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
GPT-4o mini: 39.5 (#248), Qwen3 Max: 62.4 (#76)
| Benchmark | GPT-4o mini | Qwen3 Max |
|---|---|---|
| LMArena Text | 1286 | 1439 |
| LMArena Creative Writing | 1268 | 1402 |
| LMArena Multi-Turn | 1285 | 1446 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than Qwen3 Max?
Qwen3 Max is the stronger model overall, scoring 43.7 to 25.5 on the Noometry Index. GPT-4o mini costs 9.1× less per token, which makes it the better buy when Qwen3 Max's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or Qwen3 Max?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is GPT-4o mini or Qwen3 Max better for coding?
Qwen3 Max scores higher on coding benchmarks: 43.0 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 128K.
How many benchmarks do GPT-4o mini and Qwen3 Max share?
28 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Qwen3 Max has 33.