# GPT-4.5 vs Qwen3.8 Max

> Qwen3.8 Max is the stronger model overall, scoring 56.8 to 37.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-qwen3-8-max
- Last updated: 2026-10-10
- Shared benchmarks: 20

## Summary

- They share 20 benchmarks with published results for both. GPT-4.5 scores higher in 1 category and Qwen3.8 Max in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 32.6.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 100% for Qwen3.8 Max.

## Snapshot

| | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 37.2 | 56.8 |
| Rank | 208 | 22 |
| Context | — | 1M |
| Input $/M | — | $2 |
| Output $/M | — | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.5: 42.2 (#109)
- Qwen3.8 Max: 53.5 (#29)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1396 | 1502 |
| DeepSWE | — | 57.5% |
| Aider Polyglot | 44.9% | — |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |

## Agentic & Tool Use

- GPT-4.5: 27.9 (#97)
- Qwen3.8 Max: 45.4 (#14)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| Cybench | 17.5% | — |
| GDP.pdf | — | 23.2% |

## Reasoning

- GPT-4.5: 13.9 (#330)
- Qwen3.8 Max: 54.4 (#26)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1403 | 1496 |
| Epoch Capabilities Index | 136.74 | 156.41 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| NYT Connections (extended) | — | 88.3% |
| ARC-AGI-1 | 10.3% | — |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LiveBench Data Analysis | 64.3% | — |
| LMCA | — | 46.2% |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |

## Math

- GPT-4.5: 32.6 (#211)
- Qwen3.8 Max: 73.2 (#20)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 100% |
| LMArena Math | 1412 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| LiveBench Math | 69.3% | — |
| MATH Level 5 | 78.6% | — |

## Knowledge

- GPT-4.5: 32.5 (#211)
- Qwen3.8 Max: 61.7 (#27)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 68.7% | 92.7% |
| LMArena Expert | 1394 | 1507 |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | — | 47.3% |
| Confabulations | 13.6% | — |

## Multimodal

- GPT-4.5: 37.6 (#71)
- Qwen3.8 Max: 37.2 (#75)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | 1195 | 1314 |
| VPCT | 45% | — |
| Furniture Assembly | — | 20% |

## Multilingual

- GPT-4.5: 52.5 (#83)
- Qwen3.8 Max: 56.7 (#18)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1413 | 1472 |
| LMArena Chinese | 1421 | 1538 |
| LMArena French | 1418 | 1503 |
| LMArena German | 1457 | 1483 |
| LMArena Japanese | 1416 | 1467 |
| LMArena Korean | 1392 | 1461 |
| LMArena Russian | 1419 | 1481 |
| LMArena Spanish | — | 1492 |

## Instruction Following

- GPT-4.5: 72.6 (#134)
- Qwen3.8 Max: 77.6 (#17)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1404 | 1479 |
| LiveBench Instruction Following | 72.3% | — |

## Long Context

- GPT-4.5: 40.4 (#155)
- Qwen3.8 Max: 45.6 (#31)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1406 | 1489 |
| Fiction.LiveBench | 63.9% | — |

## Writing & Preference

- GPT-4.5: 56.9 (#134)
- Qwen3.8 Max: 67.1 (#30)

| Benchmark | GPT-4.5 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1417 | 1483 |
| LMArena Creative Writing | 1394 | 1479 |
| LMArena Multi-Turn | 1444 | 1489 |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than Qwen3.8 Max?

Qwen3.8 Max is the stronger model overall, scoring 56.8 to 37.2 on the Noometry Index.

### Is GPT-4.5 or Qwen3.8 Max better for coding?

Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 42.2 in the Noometry coding category.

### How many benchmarks do GPT-4.5 and Qwen3.8 Max share?

20 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen3.8 Max has 39.