# o1-mini vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 34.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/o1-mini-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. o1-mini scores higher in 0 categories and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.8 Max leads 54.4 to 8.8.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 46.9% for o1-mini and 100% for Qwen3.8 Max.

## Snapshot

| | o1-mini | Qwen3.8 Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 34.0 | 56.8 |
| Rank | 235 | 22 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- o1-mini: 35.5 (#224)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1362 | 1502 |
| DeepSWE | — | 57.5% |
| Aider Polyglot | 32.9% | — |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| WeirdML | 36.3% | — |
| LiveBench Coding | 48% | — |
| HumanEval+ | 89% | — |
| MBPP+ | 78.8% | — |

## Agentic & Tool Use

- o1-mini: 24.6 (#118)
- Qwen3.8 Max: 45.4 (#14)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| Cybench | 10% | — |
| GDP.pdf | — | 23.2% |

## Reasoning

- o1-mini: 8.8 (#346)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1333 | 1496 |
| Epoch Capabilities Index | 135.82 | 156.41 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 18.1% | — |
| NYT Connections (extended) | — | 88.3% |
| ARC-AGI-1 | 14% | — |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| LiveBench Reasoning | 72.3% | — |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | — | 46.2% |
| LiveBench | 57.8% | — |

## Math

- o1-mini: 35.4 (#186)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 46.9% | 100% |
| LMArena Math | 1358 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| LiveBench Math | 62% | — |
| MATH Level 5 | 89.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |

## Knowledge

- o1-mini: 34.9 (#192)
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 62.4% | 92.7% |
| LMArena Expert | 1316 | 1507 |
| SimpleQA Verified | — | 47.3% |
| Confabulations | 18.6% | — |

## Multimodal

- o1-mini: —
- Qwen3.8 Max: 37.2 (#75)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |

## Multilingual

- o1-mini: 43.6 (#182)
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1289 | 1472 |
| LMArena Chinese | 1314 | 1538 |
| LMArena French | 1293 | 1503 |
| LMArena German | 1278 | 1483 |
| LMArena Japanese | 1245 | 1467 |
| LMArena Korean | 1223 | 1461 |
| LMArena Russian | 1283 | 1481 |
| LMArena Spanish | 1303 | 1492 |

## Instruction Following

- o1-mini: 66.7 (#206)
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1304 | 1479 |
| LiveBench Instruction Following | 65.4% | — |

## Long Context

- o1-mini: 40.1 (#161)
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1320 | 1489 |

## Writing & Preference

- o1-mini: 48.4 (#202)
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | o1-mini | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1317 | 1483 |
| LMArena Creative Writing | 1244 | 1479 |
| LMArena Multi-Turn | 1314 | 1489 |
| Short-Story Creative Writing | 64.9% | — |
| LiveBench Language | 40.9% | — |

## FAQ

### Is o1-mini better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 34.0 on the Noometry Index.

### Is o1-mini or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 35.5 in the Noometry coding category.

### How many benchmarks do o1-mini and Qwen3.8 Max share?

20 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and Qwen3.8 Max has 39.