# GPT-5.3 Chat vs Qwen2.5 72B Instruct

> GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 2.0× less per token, which makes it the better buy when GPT-5.3 Chat's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-5-3-chat-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. GPT-5.3 Chat scores higher in 8 categories and Qwen2.5 72B Instruct in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.3 Chat leads 38.2 to 19.3.
- Qwen2.5 72B Instruct is cheaper at $1.40 / $5.60 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.
- Qwen2.5 72B Instruct accepts more context: 131K tokens versus 128K.
- Qwen2.5 72B Instruct has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 42.8 | 31.9 |
| Rank | 109 | 267 |
| Context | 128K | 131K |
| Input $/M | $1.75 | $1.40 |
| Output $/M | $14 | $5.60 |
| Weights | Proprietary | Open |

## Coding

- GPT-5.3 Chat: 41.4 (#124)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Coding | 1408 | 1292 |
| WeirdML | — | 16% |
| BigCodeBench Instruct | — | 45.8% |
| BigCodeBench Complete | — | 55.9% |

## Agentic & Tool Use

- GPT-5.3 Chat: —
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| TheAgentCompany | — | 5.7% |
| BALROG | — | 16.2% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- GPT-5.3 Chat: 28.5 (#102)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1271 |
| DTBench | — | 62.9% |
| LMCA | — | 13.4% |
| BIG-Bench Hard | — | 79.8% |
| Epoch Capabilities Index | — | 129 |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| PIQA | — | 82.6% |
| WinoGrande | — | 82.3% |

## Math

- GPT-5.3 Chat: 38.2 (#142)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Math | 1389 | 1283 |
| OTIS Mock AIME 2024-2025 | — | 8.1% |
| Omni-MATH | — | 33% |
| MATH Level 5 | — | 63.2% |

## Knowledge

- GPT-5.3 Chat: 38.8 (#140)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Expert | 1397 | 1245 |
| GPQA Diamond | — | 49.1% |
| MMLU-Pro | — | 63.1% |
| Confabulations | — | 19.1% |
| GPQA (HELM) | — | 42.6% |
| ARC (AI2) Challenge | — | 94.5% |
| MMLU | — | 85.3% |
| TriviaQA | — | 71.9% |

## Multilingual

- GPT-5.3 Chat: 50.3 (#124)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1382 | 1252 |
| LMArena Chinese | 1432 | 1272 |
| LMArena French | 1397 | 1280 |
| LMArena German | 1384 | 1234 |
| LMArena Japanese | 1352 | 1180 |
| LMArena Korean | 1346 | 1188 |
| LMArena Russian | 1400 | 1264 |
| LMArena Spanish | 1371 | 1256 |

## Instruction Following

- GPT-5.3 Chat: 72.8 (#129)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Instruction Following | 1378 | 1254 |
| IFEval | — | 80.6% |

## Long Context

- GPT-5.3 Chat: 42.6 (#120)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1396 | 1282 |

## Writing & Preference

- GPT-5.3 Chat: 63.1 (#68)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | GPT-5.3 Chat | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1389 | 1269 |
| LMArena Creative Writing | 1355 | 1221 |
| LMArena Multi-Turn | 1412 | 1272 |
| EQ-Bench Creative Writing | 1690 | — |
| WildBench | — | 80.2% |

## FAQ

### Is GPT-5.3 Chat better than Qwen2.5 72B Instruct?

GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 31.9 on the Noometry Index. Qwen2.5 72B Instruct costs 2.0× less per token, which makes it the better buy when GPT-5.3 Chat's lead doesn't matter for your workload.

### Which is cheaper, GPT-5.3 Chat or Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is cheaper. It lists at $1.40 per million input tokens and $5.60 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.

### Is GPT-5.3 Chat or Qwen2.5 72B Instruct better for coding?

GPT-5.3 Chat scores higher on coding benchmarks: 41.4 versus 33.2 in the Noometry coding category.

### Which has the bigger context window?

Qwen2.5 72B Instruct does, with 131K tokens against 128K.

### How many benchmarks do GPT-5.3 Chat and Qwen2.5 72B Instruct share?

17 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Qwen2.5 72B Instruct has 43.