Model comparison
o1 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 40.9 on the Noometry Index.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. o1 scores higher in 1 category and Qwen3.8 Max in 9 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 36.1.
- The biggest single-benchmark swing is FrontierMath (Tiers 1-3): 14.7% for o1 and 74.7% for Qwen3.8 Max.
- Qwen3.8 Max is cheaper at $2 / $6 per million input/output tokens, against $15 / $60 for o1.
- Qwen3.8 Max accepts more context: 1M tokens versus 200K.
Side by side
| o1 | Qwen3.8 Max | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 40.9 | 56.8 |
| Released | 2024-09-12 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 1M |
| Max output | 100K | 131K |
| Input $ / M tokens | $15 | $2 |
| Output $ / M tokens | $60 | $6 |
| Results tracked | 52 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
o1: 46.1 (#70), Qwen3.8 Max: 53.5 (#29)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1367 | 1502 |
| DeepSWE | — | 57.5% |
| Aider Polyglot | 61.7% | — |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| WeirdML | 47.6% | — |
| LiveBench Coding | 69.7% | — |
| CadEval | 56% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 80.2% | — |
Agentic & Tool Use Qwen3.8 Max leads
o1: 24.6 (#117), Qwen3.8 Max: 45.4 (#14)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| Cybench | 10% | — |
| GDP.pdf | — | 23.2% |
| METR Time Horizons | 51.1% | — |
Reasoning Qwen3.8 Max leads
o1: 27.9 (#111), Qwen3.8 Max: 54.4 (#26)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| Chess Puzzles | 15% | 40% |
| LMArena Hard Prompts | 1371 | 1496 |
| DTBench | 74.7% | 92% |
| LMCA | 22.3% | 46.2% |
| Epoch Capabilities Index | 141.91 | 156.41 |
| SimpleBench | 41.7% | — |
| NYT Connections (extended) | — | 88.3% |
| ARC-AGI-1 | 30.7% | — |
| CritPt | — | 20% |
| EnigmaEval | 5.7% | — |
| LiveBench Reasoning | 91.6% | — |
| Mystery Game Puzzles | — | 38% |
| LiveBench Data Analysis | 65.5% | — |
| LiveBench | 75.7% | — |
Math Qwen3.8 Max leads
o1: 36.1 (#175), Qwen3.8 Max: 73.2 (#20)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 14.7% | 74.7% |
| OTIS Mock AIME 2024-2025 | 73.3% | 100% |
| LMArena Math | 1388 | 1499 |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| LiveBench Math | 80.3% | — |
| MATH Level 5 | 94.7% | — |
| FrontierMath (Feb 2025 set) | 9.3% | — |
Knowledge Qwen3.8 Max leads
o1: 41.5 (#110), Qwen3.8 Max: 61.7 (#27)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 76.8% | 92.7% |
| SimpleQA Verified | 41.1% | 47.3% |
| LMArena Expert | 1361 | 1507 |
| Humanity's Last Exam | 8% | — |
| Confabulations | 11.7% | — |
Multimodal Qwen3.8 Max leads
o1: 34.2 (#93), Qwen3.8 Max: 37.2 (#75)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 1168 | 1314 |
| GeoBench | 80% | — |
| VPCT | 37% | — |
| Furniture Assembly | — | 20% |
| SpatialViz-Bench | 41.4% | — |
Multilingual Qwen3.8 Max leads
o1: 48.6 (#142), Qwen3.8 Max: 56.7 (#18)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1358 | 1472 |
| LMArena Chinese | 1394 | 1538 |
| LMArena French | 1344 | 1503 |
| LMArena German | 1337 | 1483 |
| LMArena Japanese | 1346 | 1467 |
| LMArena Korean | 1396 | 1461 |
| LMArena Russian | 1356 | 1481 |
| LMArena Spanish | 1345 | 1492 |
Instruction Following Qwen3.8 Max leads
o1: 74.8 (#86), Qwen3.8 Max: 77.6 (#17)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1367 | 1479 |
| LiveBench Instruction Following | 81.5% | — |
Long Context o1 leads
o1: 50.3 (#9), Qwen3.8 Max: 45.6 (#31)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1378 | 1489 |
| Fiction.LiveBench | 83.3% | — |
Writing & Preference Qwen3.8 Max leads
o1: 55.6 (#144), Qwen3.8 Max: 67.1 (#30)
| Benchmark | o1 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1366 | 1483 |
| LMArena Creative Writing | 1348 | 1479 |
| LMArena Multi-Turn | 1369 | 1489 |
| Short-Story Creative Writing | 70.2% | — |
| LiveBench Language | 65.4% | — |
Frequently asked questions
Is o1 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 40.9 on the Noometry Index.
Which is cheaper, o1 or Qwen3.8 Max?
Qwen3.8 Max is cheaper. It lists at $2 per million input tokens and $6 per million output tokens; o1 lists at $15 and $60.
Is o1 or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 46.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 200K.
How many benchmarks do o1 and Qwen3.8 Max share?
26 benchmarks have published results for both models. o1 has 52 scored results on Noometry and Qwen3.8 Max has 39.