# GPT-5.5 Pro vs Qwen3.7 Max

> GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 51.5 on the Noometry Index. Qwen3.7 Max costs 18× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-5-pro-vs-qwen3-7-max
- Last updated: 2026-10-12
- Shared benchmarks: 10

## Summary

- They share 10 benchmarks with published results for both. GPT-5.5 Pro scores higher in 3 categories and Qwen3.7 Max in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.5 Pro leads 73.3 to 49.2.
- The biggest single-benchmark swing is Chess Puzzles: 64% for GPT-5.5 Pro and 19% for Qwen3.7 Max.
- Qwen3.7 Max is cheaper at $2.50 / $7.50 per million input/output tokens, against $30 / $180 for GPT-5.5 Pro.
- GPT-5.5 Pro accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 64.3 | 51.5 |
| Rank | 8 | 42 |
| Context | 1.05M | 1M |
| Input $/M | $30 | $2.50 |
| Output $/M | $180 | $7.50 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.5 Pro: —
- Qwen3.7 Max: 50.4 (#45)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| SWE-bench Verified | — | 77.3% |
| LMArena WebDev | — | 1515 |
| SciCode | — | 48.8% |
| LMArena Coding | — | 1498 |
| ALE-Bench | — | 1,189 |

## Agentic & Tool Use

- GPT-5.5 Pro: —
- Qwen3.7 Max: 22.1 (#135)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| GBAEval | — | 0.4% |

## Reasoning

- GPT-5.5 Pro: 73.3 (#10)
- Qwen3.7 Max: 49.2 (#38)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| SimpleBench | 76.9% | 70.4% |
| CritPt | 30.6% | 13.4% |
| Chess Puzzles | 64% | 19% |
| DTBench | 96% | 92.3% |
| LMCA | 53.9% | 44% |
| Epoch Capabilities Index | 162.07 | 153.68 |
| ARC-AGI-2 | 84.6% | — |
| NYT Connections (extended) | — | 85.1% |
| ARC-AGI-1 | 96.5% | — |
| EBR-Bench | — | 9.5% |
| LMArena Hard Prompts | — | 1483 |
| Mystery Game Puzzles | — | 32% |

## Math

- GPT-5.5 Pro: 84.0 (#10)
- Qwen3.7 Max: 62.4 (#32)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87.7% | 64.6% |
| FrontierMath Tier 4 | 78% | 34.1% |
| OTIS Mock AIME 2024-2025 | 100% | 95.6% |
| ProofBench | — | 26% |
| LMArena Math | — | 1490 |
| FrontierMath (Feb 2025 set) | 52.4% | — |
| FrontierMath Tier 4 (v1) | 39.6% | — |

## Knowledge

- GPT-5.5 Pro: 64.1 (#19)
- Qwen3.7 Max: 61.6 (#28)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| GPQA Diamond | 93.9% | 90.9% |
| SimpleQA Verified | — | 55.8% |
| LMArena Expert | — | 1488 |

## Multilingual

- GPT-5.5 Pro: —
- Qwen3.7 Max: 56.9 (#15)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| LMArena Non-English | — | 1474 |
| LMArena Chinese | — | 1530 |
| LMArena Russian | — | 1484 |

## Instruction Following

- GPT-5.5 Pro: —
- Qwen3.7 Max: 76.7 (#38)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| LMArena Instruction Following | — | 1460 |

## Long Context

- GPT-5.5 Pro: —
- Qwen3.7 Max: 45.4 (#40)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| LMArena Longer Query | — | 1482 |

## Writing & Preference

- GPT-5.5 Pro: —
- Qwen3.7 Max: 65.0 (#54)

| Benchmark | GPT-5.5 Pro | Qwen3.7 Max |
|---|---|---|
| LMArena Text | — | 1476 |
| LMArena Creative Writing | — | 1449 |
| EQ-Bench 4 | — | 1110 |
| LMArena Multi-Turn | — | 1481 |

## FAQ

### Is GPT-5.5 Pro better than Qwen3.7 Max?

GPT-5.5 Pro is the stronger model overall, scoring 64.3 to 51.5 on the Noometry Index. Qwen3.7 Max costs 18× less per token, which makes it the better buy when GPT-5.5 Pro's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.5 Pro or Qwen3.7 Max?

Qwen3.7 Max is cheaper. It lists at $2.50 per million input tokens and $7.50 per million output tokens; GPT-5.5 Pro lists at $30 and $180.

### Which has the bigger context window?

GPT-5.5 Pro does, with 1.05M tokens against 1M.

### How many benchmarks do GPT-5.5 Pro and Qwen3.7 Max share?

10 benchmarks have published results for both models. GPT-5.5 Pro has 14 scored results on Noometry and Qwen3.7 Max has 33.