Model comparison
o3-mini vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 36.7 on the Noometry Index. o3-mini costs 1.9× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
Alibaba (Qwen)Summary
- They share 25 benchmarks with published results for both. o3-mini scores higher in 1 category and Qwen3.7 Max in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Max leads 62.4 to 28.1.
- The biggest single-benchmark swing is SimpleBench: 22.8% for o3-mini and 70.4% for Qwen3.7 Max.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $2.50 / $7.50 for Qwen3.7 Max.
- Qwen3.7 Max accepts more context: 1M tokens versus 200K.
Side by side
| o3-mini | Qwen3.7 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.7 | 51.5 |
| Released | 2024-12-20 | 2026-05-19 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 100K | 131K |
| Input $ / M tokens | $1.10 | $2.50 |
| Output $ / M tokens | $4.40 | $7.50 |
| Results tracked | 51 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
o3-mini: 40.8 (#132), Qwen3.7 Max: 50.4 (#45)
| Benchmark | o3-mini | Qwen3.7 Max |
|---|---|---|
| SciCode | 39.8% | 48.8% |
| LMArena Coding | 1378 | 1498 |
| SWE-bench Verified | — | 77.3% |
| Aider Polyglot | 60.4% | — |
| LMArena WebDev | — | 1515 |
| GSO | 1.3% | — |
| WeirdML | 43.7% | — |
| LiveBench Coding | 82.7% | — |
| CadEval | 54% | — |
| ALE-Bench | — | 1,189 |
Agentic & Tool Use o3-mini leads
o3-mini: 29.6 (#84), Qwen3.7 Max: 22.1 (#135)
Reasoning Qwen3.7 Max leads
o3-mini: 16.3 (#305), Qwen3.7 Max: 49.2 (#38)
| Benchmark | o3-mini | Qwen3.7 Max |
|---|---|---|
| SimpleBench | 22.8% | 70.4% |
| CritPt | 0.3% | 13.4% |
| Chess Puzzles | 17% | 19% |
| LMArena Hard Prompts | 1366 | 1483 |
| Mystery Game Puzzles | 7% | 32% |
| DTBench | 68.8% | 92.3% |
| LMCA | 19% | 44% |
| Epoch Capabilities Index | 140.34 | 153.68 |
| ARC-AGI-2 | 3% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 34.5% | — |
| EBR-Bench | — | 9.5% |
| LiveBench Reasoning | 89.6% | — |
| LiveBench Data Analysis | 70.6% | — |
| ForecastBench | 59.6 | — |
| LiveBench | 75.9% | — |
Math Qwen3.7 Max leads
o3-mini: 28.1 (#244), Qwen3.7 Max: 62.4 (#32)
| Benchmark | o3-mini | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 18.6% | 64.6% |
| FrontierMath Tier 4 | 0% | 34.1% |
| OTIS Mock AIME 2024-2025 | 76.9% | 95.6% |
| LMArena Math | 1396 | 1490 |
| ProofBench | — | 26% |
| LiveBench Math | 77.3% | — |
| MATH Level 5 | 96.5% | — |
| FrontierMath (Feb 2025 set) | 12.4% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge Qwen3.7 Max leads
o3-mini: 38.3 (#146), Qwen3.7 Max: 61.6 (#28)
| Benchmark | o3-mini | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 77% | 90.9% |
| SimpleQA Verified | 15.3% | 55.8% |
| LMArena Expert | 1364 | 1488 |
| Confabulations | 17.9% | — |
Multilingual Qwen3.7 Max leads
o3-mini: 45.7 (#164), Qwen3.7 Max: 56.9 (#15)
| Benchmark | o3-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1319 | 1474 |
| LMArena Chinese | 1379 | 1530 |
| LMArena Russian | 1304 | 1484 |
| LMArena French | 1334 | — |
| LMArena German | 1303 | — |
| LMArena Japanese | 1286 | — |
| LMArena Korean | 1314 | — |
| LMArena Spanish | 1321 | — |
Instruction Following Qwen3.7 Max leads
o3-mini: 75.1 (#72), Qwen3.7 Max: 76.7 (#38)
| Benchmark | o3-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1337 | 1460 |
| LiveBench Instruction Following | 84.4% | — |
Long Context Qwen3.7 Max leads
o3-mini: 33.8 (#256), Qwen3.7 Max: 45.4 (#40)
| Benchmark | o3-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1343 | 1482 |
| Fiction.LiveBench | 50% | — |
Writing & Preference Qwen3.7 Max leads
o3-mini: 50.3 (#182), Qwen3.7 Max: 65.0 (#54)
| Benchmark | o3-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1337 | 1476 |
| LMArena Creative Writing | 1286 | 1449 |
| LMArena Multi-Turn | 1320 | 1481 |
| Short-Story Creative Writing | 61.7% | — |
| EQ-Bench 4 | — | 1110 |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 36.7 on the Noometry Index. o3-mini costs 1.9× less per token, which makes it the better buy when Qwen3.7 Max's lead doesn't matter for your workload.
Which is cheaper, o3-mini or Qwen3.7 Max?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; Qwen3.7 Max lists at $2.50 and $7.50.
Is o3-mini or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 200K.
How many benchmarks do o3-mini and Qwen3.7 Max share?
25 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and Qwen3.7 Max has 33.