Model comparison
GPT-4o mini vs Qwen Max
Qwen Max is the stronger model overall, scoring 34.7 to 25.5 on the Noometry Index. GPT-4o mini costs 11× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.
Last verified . 21 shared benchmarks.
Alibaba (Qwen)Summary
- They share 21 benchmarks with published results for both. GPT-4o mini scores higher in 1 category and Qwen Max in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen Max leads 25.1 to 8.7.
- The biggest single-benchmark swing is GPQA Diamond: 37.7% for GPT-4o mini and 56.1% for Qwen Max.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- GPT-4o mini accepts more context: 128K tokens versus 33K.
Side by side
| GPT-4o mini | Qwen Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 25.5 | 34.7 |
| Released | 2024-07-18 | 2024-04-03 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 33K |
| Max output | 16K | 8K |
| Input $ / M tokens | $0.15 | $1.60 |
| Output $ / M tokens | $0.60 | $6.40 |
| Results tracked | 60 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen Max leads
GPT-4o mini: 22.0 (#335), Qwen Max: 30.7 (#292)
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| Aider Polyglot | 3.6% | 21.8% |
| LMArena Coding | 1290 | 1288 |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use Not comparable
GPT-4o mini: 27.5 (#101), Qwen Max: —
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| BALROG | 17.4% | — |
Reasoning Qwen Max leads
GPT-4o mini: 8.7 (#347), Qwen Max: 25.1 (#151)
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1269 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Epoch Capabilities Index | 126.56 | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Qwen Max leads
GPT-4o mini: 10.4 (#314), Qwen Max: 22.3 (#276)
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 16.1% |
| LMArena Math | 1267 | 1275 |
| MATH Level 5 | 52.6% | 67.2% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| FrontierMath (Feb 2025 set) | — | 1% |
| GSM8K | 91.3% | — |
Knowledge Qwen Max leads
GPT-4o mini: 17.7 (#284), Qwen Max: 30.3 (#228)
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| GPQA Diamond | 37.7% | 56.1% |
| LMArena Expert | 1235 | 1248 |
| SimpleQA Verified | 8.3% | — |
| 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), Qwen Max: —
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Too close to call
GPT-4o mini: 42.0 (#199), Qwen Max: 41.8 (#202)
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| LMArena Non-English | 1266 | 1263 |
| LMArena Chinese | 1265 | 1254 |
| LMArena French | 1297 | 1330 |
| LMArena German | 1272 | 1254 |
| LMArena Japanese | 1216 | 1205 |
| LMArena Korean | 1195 | 1142 |
| LMArena Russian | 1275 | 1274 |
| LMArena Spanish | 1276 | 1290 |
Instruction Following Qwen Max leads
GPT-4o mini: 61.9 (#239), Qwen Max: 66.5 (#208)
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| LMArena Instruction Following | 1258 | 1262 |
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
Long Context Too close to call
GPT-4o mini: 39.1 (#186), Qwen Max: 39.4 (#180)
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| LMArena Longer Query | 1289 | 1288 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference Qwen Max leads
GPT-4o mini: 39.5 (#248), Qwen Max: 47.8 (#205)
| Benchmark | GPT-4o mini | Qwen Max |
|---|---|---|
| LMArena Text | 1286 | 1282 |
| LMArena Creative Writing | 1268 | 1248 |
| LMArena Multi-Turn | 1285 | 1277 |
| 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 Qwen Max?
Qwen Max is the stronger model overall, scoring 34.7 to 25.5 on the Noometry Index. GPT-4o mini costs 11× less per token, which makes it the better buy when Qwen Max's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or Qwen Max?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is GPT-4o mini or Qwen Max better for coding?
Qwen Max scores higher on coding benchmarks: 30.7 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
GPT-4o mini does, with 128K tokens against 33K.
How many benchmarks do GPT-4o mini and Qwen Max share?
21 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Qwen Max has 23.