# GPT-6 Sol vs Qwen2.5-Max

> GPT-6 Sol is the stronger model overall, scoring 49.2 to 40.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-6-sol-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 13

## Summary

- They share 13 benchmarks with published results for both. GPT-6 Sol scores higher in 8 categories and Qwen2.5-Max in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-6 Sol leads 49.3 to 24.6.

## Snapshot

| | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 49.2 | 40.1 |
| Rank | 46 | 142 |
| Context | 1.05M | — |
| Input $/M | $2 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-6 Sol: 59.6 (#11)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1453 | 1359 |
| DeepSWE | 68.8% | — |
| FrontierCode | 49.3% | — |
| LMArena WebDev | 1692 | — |
| LiveBench Coding | — | 64.4% |

## Agentic & Tool Use

- GPT-6 Sol: 33.5 (#49)
- Qwen2.5-Max: —

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| GDP.pdf | 28% | — |

## Reasoning

- GPT-6 Sol: 49.3 (#34)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1420 | 1360 |
| NYT Connections (extended) | 90.1% | — |
| EBR-Bench | 53.3% | — |
| LiveBench Reasoning | — | 51.4% |
| LiveBench Data Analysis | — | 67.9% |
| Epoch Capabilities Index | — | 132.54 |
| LiveBench | — | 62.3% |

## Math

- GPT-6 Sol: 35.8 (#135)
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1404 | 1369 |
| LiveBench Math | — | 58.4% |

## Knowledge

- GPT-6 Sol: 43.0 (#87)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| LMArena Expert | 1449 | 1337 |
| Confabulations | — | 21.8% |
| Vectara Hallucination Rate | 6.5% | — |

## Multimodal

- GPT-6 Sol: 47.6 (#9)
- Qwen2.5-Max: —

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| Furniture Assembly | 58.3% | — |

## Multilingual

- GPT-6 Sol: 51.0 (#113)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1389 | 1352 |
| LMArena Chinese | 1416 | 1382 |
| LMArena Russian | 1407 | 1353 |
| LMArena Spanish | 1377 | 1377 |
| LMArena French | — | 1396 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1299 |
| LMArena Korean | — | 1304 |

## Instruction Following

- GPT-6 Sol: 74.4 (#97)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1406 | 1335 |
| LiveBench Instruction Following | — | 75.3% |

## Long Context

- GPT-6 Sol: 43.2 (#100)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1415 | 1358 |

## Writing & Preference

- GPT-6 Sol: 72.3 (#15)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | GPT-6 Sol | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1396 | 1367 |
| LMArena Creative Writing | 1392 | 1339 |
| LMArena Multi-Turn | 1405 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| EQ-Bench Creative Writing | 2125 | — |
| LiveBench Language | — | 56.3% |

## FAQ

### Is GPT-6 Sol better than Qwen2.5-Max?

GPT-6 Sol is the stronger model overall, scoring 49.2 to 40.1 on the Noometry Index.

### Is GPT-6 Sol or Qwen2.5-Max better for coding?

GPT-6 Sol scores higher on coding benchmarks: 59.6 versus 41.2 in the Noometry coding category.

### How many benchmarks do GPT-6 Sol and Qwen2.5-Max share?

13 benchmarks have published results for both models. GPT-6 Sol has 22 scored results on Noometry and Qwen2.5-Max has 27.