# GPT-4 Turbo vs Qwen3 Max

> Qwen3 Max is the stronger model overall, scoring 43.7 to 30.5 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4-turbo-vs-qwen3-max
- Last updated: 2026-10-12
- Shared benchmarks: 25

## Summary

- They share 25 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and Qwen3 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 Max leads 38.7 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 73.3% for Qwen3 Max.
- Qwen3 Max is cheaper at $1.20 / $6 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- Qwen3 Max accepts more context: 262K tokens versus 128K.

## Snapshot

| | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 30.5 | 43.7 |
| Rank | 292 | 87 |
| Context | 128K | 262K |
| Input $/M | $10 | $1.20 |
| Output $/M | $30 | $6 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4 Turbo: 33.8 (#249)
- Qwen3 Max: 43.0 (#93)

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1268 | 1456 |
| WeirdML | 18% | — |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| ALE-Bench | — | 370.45 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |

## Agentic & Tool Use

- GPT-4 Turbo: —
- Qwen3 Max: —

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| METR Time Horizons | 36.7% | — |
| Vending-Bench 2 | — | 71.56 |

## Reasoning

- GPT-4 Turbo: 15.3 (#317)
- Qwen3 Max: 22.6 (#190)

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| Chess Puzzles | 6% | 4% |
| LMArena Hard Prompts | 1251 | 1448 |
| DTBench | 61.6% | 82.1% |
| LMCA | 9.8% | 28.3% |
| Epoch Capabilities Index | 127.25 | 142.38 |
| SimpleBench | 25.1% | — |
| Kagi LLM Benchmark | — | 72.5% |
| NYT Connections (extended) | — | 30.1% |
| Mystery Game Puzzles | — | 5% |
| ForecastBench | 59.4 | — |

## Math

- GPT-4 Turbo: 9.0 (#322)
- Qwen3 Max: 38.7 (#131)

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 18.9% |
| OTIS Mock AIME 2024-2025 | 6.7% | 73.3% |
| LMArena Math | 1272 | 1446 |
| MATH Level 5 | 46.7% | 97.1% |

## Knowledge

- GPT-4 Turbo: 24.3 (#268)
- Qwen3 Max: 48.1 (#78)

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 46.6% | 72.6% |
| LMArena Expert | 1223 | 1455 |
| SimpleQA Verified | — | 48.7% |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |

## Multimodal

- GPT-4 Turbo: 30.6 (#110)
- Qwen3 Max: —

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| LMArena Vision | 1090 | — |

## Multilingual

- GPT-4 Turbo: 40.5 (#216)
- Qwen3 Max: 53.7 (#62)

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1245 | 1429 |
| LMArena Chinese | 1242 | 1478 |
| LMArena French | 1276 | 1449 |
| LMArena German | 1259 | 1463 |
| LMArena Japanese | 1194 | 1397 |
| LMArena Korean | 1187 | 1399 |
| LMArena Russian | 1259 | 1428 |
| LMArena Spanish | 1260 | 1462 |

## Instruction Following

- GPT-4 Turbo: 65.8 (#216)
- Qwen3 Max: 74.8 (#87)

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1249 | 1419 |

## Long Context

- GPT-4 Turbo: 38.0 (#206)
- Qwen3 Max: 41.6 (#134)

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| LMArena Longer Query | 1254 | 1438 |
| Fiction.LiveBench | — | 66.7% |
| CL-bench | — | 14.5% |

## Writing & Preference

- GPT-4 Turbo: 47.7 (#206)
- Qwen3 Max: 62.4 (#76)

| Benchmark | GPT-4 Turbo | Qwen3 Max |
|---|---|---|
| LMArena Text | 1272 | 1439 |
| LMArena Creative Writing | 1269 | 1402 |
| LMArena Multi-Turn | 1267 | 1446 |

## FAQ

### Is GPT-4 Turbo better than Qwen3 Max?

Qwen3 Max is the stronger model overall, scoring 43.7 to 30.5 on the Noometry Index.

### Which is cheaper, GPT-4 Turbo or Qwen3 Max?

Qwen3 Max is cheaper. It lists at $1.20 per million input tokens and $6 per million output tokens; GPT-4 Turbo lists at $10 and $30.

### Is GPT-4 Turbo or Qwen3 Max better for coding?

Qwen3 Max scores higher on coding benchmarks: 43.0 versus 33.8 in the Noometry coding category.

### Which has the bigger context window?

Qwen3 Max does, with 262K tokens against 128K.

### How many benchmarks do GPT-4 Turbo and Qwen3 Max share?

25 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Qwen3 Max has 33.