# GPT-4.5 vs Qwen3.5 Plus

> Qwen3.5 Plus is the stronger model overall, scoring 42.3 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-5-vs-qwen3-5-plus
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. GPT-4.5 scores higher in 0 categories and Qwen3.5 Plus in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.5 Plus leads 32.0 to 14.1.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 37.8% for GPT-4.5 and 86.7% for Qwen3.5 Plus.

## Snapshot

| | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 36.9 | 42.3 |
| Rank | 200 | 103 |
| Context | — | 1M |
| Input $/M | — | $0.40 |
| Output $/M | — | $2.40 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4.5: 41.8 (#102)
- Qwen3.5 Plus: —

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| Aider Polyglot | 44.9% | — |
| WeirdML | 39.4% | — |
| LiveBench Coding | 75.2% | — |
| LMArena Coding | 1397 | — |
| ALE-Bench | — | 621.92 |

## Agentic & Tool Use

- GPT-4.5: 27.6 (#92)
- Qwen3.5 Plus: —

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| Cybench | 17.5% | — |
| Vending-Bench 2 | — | 0.54 |

## Reasoning

- GPT-4.5: 14.1 (#320)
- Qwen3.5 Plus: 32.0 (#67)

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| Epoch Capabilities Index | 136.74 | 146.79 |
| ARC-AGI-2 | 0.8% | — |
| SimpleBench | 34.5% | — |
| ARC-AGI-1 | 10.3% | — |
| Chess Puzzles | — | 22% |
| EnigmaEval | 3.2% | — |
| LiveBench Reasoning | 71.1% | — |
| LMArena Hard Prompts | 1404 | — |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 80.5% |
| LiveBench Data Analysis | 64.3% | — |
| LMCA | — | 36.4% |
| ForecastBench | 61.7 | — |
| LiveBench | 69% | — |

## Math

- GPT-4.5: 31.0 (#200)
- Qwen3.5 Plus: 47.9 (#55)

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 37.8% | 86.7% |
| LiveBench Math | 69.3% | — |
| LMArena Math | 1412 | — |
| MATH Level 5 | 78.6% | — |
| FrontierMath (Feb 2025 set) | — | 21% |
| FrontierMath Tier 4 (v1) | — | 2.1% |

## Knowledge

- GPT-4.5: 32.4 (#205)
- Qwen3.5 Plus: 46.0 (#78)

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| GPQA Diamond | 68.7% | 84.8% |
| Humanity's Last Exam | 5.4% | — |
| SimpleQA Verified | — | 25.4% |
| Confabulations | 13.6% | — |
| Vectara Hallucination Rate | — | 10.7% |
| LMArena Expert | 1394 | — |

## Multimodal

- GPT-4.5: 37.0 (#68)
- Qwen3.5 Plus: —

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| LMArena Vision | 1195 | — |
| VPCT | 45% | — |

## Multilingual

- GPT-4.5: 52.7 (#78)
- Qwen3.5 Plus: —

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| LMArena Non-English | 1413 | — |
| LMArena Chinese | 1421 | — |
| LMArena French | 1417 | — |
| LMArena German | 1457 | — |
| LMArena Japanese | 1416 | — |
| LMArena Korean | 1392 | — |
| LMArena Russian | 1419 | — |

## Instruction Following

- GPT-4.5: 72.8 (#129)
- Qwen3.5 Plus: —

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| LiveBench Instruction Following | 72.3% | — |
| LMArena Instruction Following | 1404 | — |

## Long Context

- GPT-4.5: 40.4 (#150)
- Qwen3.5 Plus: 42.9 (#109)

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| Fiction.LiveBench | 63.9% | — |
| CL-bench | — | 19.8% |
| CL-bench Life | — | 12.4% |
| LMArena Longer Query | 1406 | — |

## Writing & Preference

- GPT-4.5: 57.1 (#129)
- Qwen3.5 Plus: —

| Benchmark | GPT-4.5 | Qwen3.5 Plus |
|---|---|---|
| LMArena Text | 1417 | — |
| LMArena Creative Writing | 1394 | — |
| Short-Story Creative Writing | 75.6% | — |
| EQ-Bench Creative Writing | 1258 | — |
| LMArena Multi-Turn | 1444 | — |
| LiveBench Language | 61.5% | — |

## FAQ

### Is GPT-4.5 better than Qwen3.5 Plus?

Qwen3.5 Plus is the stronger model overall, scoring 42.3 to 36.9 on the Noometry Index.

### How many benchmarks do GPT-4.5 and Qwen3.5 Plus share?

3 benchmarks have published results for both models. GPT-4.5 has 42 scored results on Noometry and Qwen3.5 Plus has 15.