# GPT-6.1 Sol vs Qwen3.7 Plus

> GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 45.3 on the Noometry Index. Qwen3.7 Plus costs 5.7× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-6-1-sol-vs-qwen3-7-plus
- Last updated: 2026-10-12
- Shared benchmarks: 23

## Summary

- They share 23 benchmarks with published results for both. GPT-6.1 Sol scores higher in 8 categories and Qwen3.7 Plus in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-6.1 Sol leads 93.7 to 50.5.
- The biggest single-benchmark swing is Mystery Game Puzzles: 80% for GPT-6.1 Sol and 17% for Qwen3.7 Plus.
- Qwen3.7 Plus is cheaper at $0.40 / $1.60 per million input/output tokens, against $2 / $10 for GPT-6.1 Sol.
- GPT-6.1 Sol accepts more context: 1.05M tokens versus 1M.

## Snapshot

| | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 65.6 | 45.3 |
| Rank | 6 | 72 |
| Context | 1.05M | 1M |
| Input $/M | $2 | $0.40 |
| Output $/M | $10 | $1.60 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-6.1 Sol: 63.2 (#8)
- Qwen3.7 Plus: 36.6 (#206)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| FrontierCode | 50.2% | 10.2% |
| SciCode | 55.8% | 45.5% |
| LMArena Coding | 1487 | 1473 |
| DeepSWE | 75.2% | — |
| LMArena WebDev | 1755 | — |

## Agentic & Tool Use

- GPT-6.1 Sol: 39.6 (#26)
- Qwen3.7 Plus: 21.4 (#138)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| APEX-Agents | 60% | — |
| OSWorld 2.0 | — | 2.8% |
| GDP.pdf | 32% | — |

## Reasoning

- GPT-6.1 Sol: 81.9 (#2)
- Qwen3.7 Plus: 39.3 (#59)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 95.5% | 74.8% |
| CritPt | 31.7% | 9.1% |
| Chess Puzzles | 61% | 24% |
| LMArena Hard Prompts | 1466 | 1460 |
| Mystery Game Puzzles | 80% | 17% |
| Epoch Capabilities Index | 166.09 | 147.37 |
| ARC-AGI-2 | 94.2% | — |
| ARC-AGI-1 | 98.5% | — |
| EBR-Bench | 54.3% | — |
| DTBench | — | 84% |
| LMCA | — | 37.6% |

## Math

- GPT-6.1 Sol: 93.7 (#1)
- Qwen3.7 Plus: 50.5 (#56)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 93.7% | 34.4% |
| OTIS Mock AIME 2024-2025 | 100% | 93.3% |
| LMArena Math | 1464 | 1466 |
| FrontierMath Tier 4 | 100% | — |
| ProofBench | 99% | — |

## Knowledge

- GPT-6.1 Sol: 71.8 (#4)
- Qwen3.7 Plus: 54.9 (#51)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 95.4% | 87.9% |
| LMArena Expert | 1502 | 1467 |
| SimpleQA Verified | 73.9% | — |

## Multimodal

- GPT-6.1 Sol: 52.7 (#5)
- Qwen3.7 Plus: 41.8 (#33)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | 1288 | 1279 |
| Furniture Assembly | 80% | — |
| LMArena Document | — | 1444 |

## Multilingual

- GPT-6.1 Sol: 54.3 (#46)
- Qwen3.7 Plus: 54.8 (#38)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1438 | 1445 |
| LMArena Chinese | 1477 | 1510 |
| LMArena Russian | 1455 | 1457 |
| LMArena French | — | 1473 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1413 |
| LMArena Korean | — | 1415 |
| LMArena Spanish | — | 1457 |

## Instruction Following

- GPT-6.1 Sol: 77.0 (#29)
- Qwen3.7 Plus: 75.8 (#52)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1468 | 1440 |

## Long Context

- GPT-6.1 Sol: 44.9 (#54)
- Qwen3.7 Plus: 44.5 (#65)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1465 | 1455 |

## Writing & Preference

- GPT-6.1 Sol: 63.6 (#63)
- Qwen3.7 Plus: 64.3 (#56)

| Benchmark | GPT-6.1 Sol | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1447 | 1455 |
| LMArena Creative Writing | 1432 | 1439 |
| LMArena Multi-Turn | 1449 | 1460 |

## FAQ

### Is GPT-6.1 Sol better than Qwen3.7 Plus?

GPT-6.1 Sol is the stronger model overall, scoring 65.6 to 45.3 on the Noometry Index. Qwen3.7 Plus costs 5.7× less per token, which makes it the better buy when GPT-6.1 Sol's lead doesn't matter for your workload.

### Which is cheaper, GPT-6.1 Sol or Qwen3.7 Plus?

Qwen3.7 Plus is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; GPT-6.1 Sol lists at $2 and $10.

### Is GPT-6.1 Sol or Qwen3.7 Plus better for coding?

GPT-6.1 Sol scores higher on coding benchmarks: 63.2 versus 36.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-6.1 Sol does, with 1.05M tokens against 1M.

### How many benchmarks do GPT-6.1 Sol and Qwen3.7 Plus share?

23 benchmarks have published results for both models. GPT-6.1 Sol has 34 scored results on Noometry and Qwen3.7 Plus has 32.