# GPT-4 Turbo vs Qwen1.5-72B

> GPT-4 Turbo and Qwen1.5-72B score almost the same on the Noometry Index (30.5 vs 30.8), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-4-turbo-vs-qwen1-5-72b
- Last updated: 2026-10-10
- Shared benchmarks: 22

## Summary

- They share 22 benchmarks with published results for both. GPT-4 Turbo scores higher in 6 categories and Qwen1.5-72B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen1.5-72B leads 33.2 to 9.0.
- The biggest single-benchmark swing is BigCodeBench Complete: 58.2% for GPT-4 Turbo and 40.3% for Qwen1.5-72B.
- Qwen1.5-72B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 30.5 | 30.8 |
| Rank | 292 | 285 |
| Context | 128K | — |
| Input $/M | $10 | — |
| Output $/M | $30 | — |
| Weights | Proprietary | Open |

## Coding

- GPT-4 Turbo: 33.8 (#249)
- Qwen1.5-72B: 31.9 (#277)

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 33.2% |
| LMArena Coding | 1268 | 1165 |
| BigCodeBench Complete | 58.2% | 40.3% |
| HumanEval+ | 86.6% | 59.1% |
| MBPP+ | 73.3% | 61.6% |
| WeirdML | 18% | — |

## Agentic & Tool Use

- GPT-4 Turbo: —
- Qwen1.5-72B: —

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| METR Time Horizons | 36.7% | — |

## Reasoning

- GPT-4 Turbo: 15.3 (#317)
- Qwen1.5-72B: 22.2 (#203)

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| LMArena Hard Prompts | 1251 | 1148 |
| SimpleBench | 25.1% | — |
| Chess Puzzles | 6% | — |
| DTBench | 61.6% | — |
| LMCA | 9.8% | — |
| Epoch Capabilities Index | 127.25 | — |
| ForecastBench | 59.4 | — |

## Math

- GPT-4 Turbo: 9.0 (#322)
- Qwen1.5-72B: 33.2 (#205)

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| LMArena Math | 1272 | 1164 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.7% | — |
| MATH Level 5 | 46.7% | — |

## Knowledge

- GPT-4 Turbo: 24.3 (#268)
- Qwen1.5-72B: 11.5 (#300)

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| GPQA Diamond | 46.6% | 28.8% |
| LMArena Expert | 1223 | 1136 |
| Confabulations | 28.4% | — |
| MMLU | 81.3% | — |

## Multimodal

- GPT-4 Turbo: 30.6 (#110)
- Qwen1.5-72B: —

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| LMArena Vision | 1090 | — |

## Multilingual

- GPT-4 Turbo: 40.5 (#216)
- Qwen1.5-72B: 33.2 (#253)

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| LMArena Non-English | 1245 | 1135 |
| LMArena Chinese | 1242 | 1186 |
| LMArena French | 1276 | 1159 |
| LMArena German | 1259 | 1084 |
| LMArena Japanese | 1194 | 1061 |
| LMArena Korean | 1187 | 1050 |
| LMArena Russian | 1259 | 1104 |
| LMArena Spanish | 1260 | 1110 |

## Instruction Following

- GPT-4 Turbo: 65.8 (#216)
- Qwen1.5-72B: 59.3 (#256)

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| LMArena Instruction Following | 1249 | 1141 |

## Long Context

- GPT-4 Turbo: 38.0 (#206)
- Qwen1.5-72B: 35.1 (#243)

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| LMArena Longer Query | 1254 | 1157 |

## Writing & Preference

- GPT-4 Turbo: 47.7 (#206)
- Qwen1.5-72B: 37.3 (#258)

| Benchmark | GPT-4 Turbo | Qwen1.5-72B |
|---|---|---|
| LMArena Text | 1272 | 1166 |
| LMArena Creative Writing | 1269 | 1137 |
| LMArena Multi-Turn | 1267 | 1160 |

## FAQ

### Is GPT-4 Turbo better than Qwen1.5-72B?

GPT-4 Turbo and Qwen1.5-72B score almost the same on the Noometry Index (30.5 vs 30.8), so choose on price, context window or the category you care about most.

### Is GPT-4 Turbo or Qwen1.5-72B better for coding?

GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 31.9 in the Noometry coding category.

### How many benchmarks do GPT-4 Turbo and Qwen1.5-72B share?

22 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and Qwen1.5-72B has 22.