Model comparison
o4-mini vs Qwen3.7 Max
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 41.6 on the Noometry Index. o4-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. o4-mini scores higher in 2 categories and Qwen3.7 Max in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.7 Max leads 49.2 to 24.6.
- The biggest single-benchmark swing is SimpleQA Verified: 19.6% for o4-mini and 55.8% for Qwen3.7 Max.
- o4-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
| o4-mini | Qwen3.7 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.6 | 51.5 |
| Released | 2025-04-16 | 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 | 60 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Max leads
o4-mini: 40.9 (#127), Qwen3.7 Max: 50.4 (#45)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Coding | 1368 | 1498 |
| ALE-Bench | 826.17 | 1,189 |
| SWE-bench Verified | — | 77.3% |
| SWE-bench Verified (bash only) | 45% | — |
| Aider Polyglot | 72% | — |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| GSO | 3.6% | — |
| WeirdML | 52.6% | — |
| CadEval | 62% | — |
| AlgoTune | 1.72 | — |
Agentic & Tool Use o4-mini leads
o4-mini: 32.6 (#61), Qwen3.7 Max: 22.1 (#135)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| Berkeley Function Calling Leaderboard | 53.2% | — |
| GDPval | 25.3% | — |
| GBAEval | — | 0.4% |
| METR Time Horizons | 63.9% | — |
Reasoning Qwen3.7 Max leads
o4-mini: 24.6 (#162), Qwen3.7 Max: 49.2 (#38)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| SimpleBench | 38.7% | 70.4% |
| CritPt | 0.6% | 13.4% |
| Chess Puzzles | 26% | 19% |
| LMArena Hard Prompts | 1351 | 1483 |
| Mystery Game Puzzles | 5% | 32% |
| DTBench | 77.6% | 92.3% |
| LMCA | 26.5% | 44% |
| Epoch Capabilities Index | 145.64 | 153.68 |
| ARC-AGI-2 | 6.1% | — |
| Kagi LLM Benchmark | 67.6% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 58.7% | — |
| EnigmaEval | 9.2% | — |
| EBR-Bench | — | 9.5% |
| ForecastBench | 61.8 | — |
Math Qwen3.7 Max leads
o4-mini: 40.8 (#89), Qwen3.7 Max: 62.4 (#32)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 36.1% | 64.6% |
| FrontierMath Tier 4 | 4.9% | 34.1% |
| OTIS Mock AIME 2024-2025 | 81.7% | 95.6% |
| LMArena Math | 1389 | 1490 |
| ProofBench | — | 26% |
| Omni-MATH | 72% | — |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 24.8% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
Knowledge Qwen3.7 Max leads
o4-mini: 43.6 (#91), Qwen3.7 Max: 61.6 (#28)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 79.6% | 90.9% |
| SimpleQA Verified | 19.6% | 55.8% |
| LMArena Expert | 1343 | 1488 |
| Humanity's Last Exam | 18.1% | — |
| MMLU-Pro | 82% | — |
| Confabulations | 15.8% | — |
| Vectara Hallucination Rate | 18.6% | — |
| GPQA (HELM) | 73.5% | — |
Multimodal Not comparable
o4-mini: 40.2 (#49), Qwen3.7 Max: —
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Vision | 1194 | — |
| GeoBench | 64% | — |
| VPCT | 57.5% | — |
Multilingual Qwen3.7 Max leads
o4-mini: 47.0 (#154), Qwen3.7 Max: 56.9 (#15)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | 1337 | 1474 |
| LMArena Chinese | 1354 | 1530 |
| LMArena Russian | 1334 | 1484 |
| LMArena French | 1364 | — |
| LMArena German | 1336 | — |
| LMArena Japanese | 1308 | — |
| LMArena Korean | 1312 | — |
| LMArena Spanish | 1347 | — |
Instruction Following Qwen3.7 Max leads
o4-mini: 75.2 (#68), Qwen3.7 Max: 76.7 (#38)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | 1321 | 1460 |
| IFEval | 92.8% | — |
Long Context Too close to call
o4-mini: 45.5 (#33), Qwen3.7 Max: 45.4 (#40)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | 1315 | 1482 |
| Fiction.LiveBench | 77.8% | — |
Writing & Preference Qwen3.7 Max leads
o4-mini: 54.0 (#152), Qwen3.7 Max: 65.0 (#54)
| Benchmark | o4-mini | Qwen3.7 Max |
|---|---|---|
| LMArena Text | 1353 | 1476 |
| LMArena Creative Writing | 1294 | 1449 |
| LMArena Multi-Turn | 1350 | 1481 |
| Short-Story Creative Writing | 75% | — |
| WildBench | 85.4% | — |
| EQ-Bench 4 | — | 1110 |
Frequently asked questions
Is o4-mini better than Qwen3.7 Max?
Qwen3.7 Max is the stronger model overall, scoring 51.5 to 41.6 on the Noometry Index. o4-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, o4-mini or Qwen3.7 Max?
o4-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 o4-mini or Qwen3.7 Max better for coding?
Qwen3.7 Max scores higher on coding benchmarks: 50.4 versus 40.9 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Max does, with 1M tokens against 200K.
How many benchmarks do o4-mini and Qwen3.7 Max share?
25 benchmarks have published results for both models. o4-mini has 60 scored results on Noometry and Qwen3.7 Max has 33.