# GPT-4o mini vs Qwen2.5 72B Instruct

> Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 25.5 on the Noometry Index. GPT-4o mini costs 9.3× less per token, which makes it the better buy when Qwen2.5 72B Instruct's lead doesn't matter for your workload.

- Canonical page: https://noometry.com/compare/gpt-4o-mini-vs-qwen2-5-72b-instruct
- Last updated: 2026-10-12
- Shared benchmarks: 35

## Summary

- They share 35 benchmarks with published results for both. GPT-4o mini scores higher in 3 categories and Qwen2.5 72B Instruct in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen2.5 72B Instruct leads 22.3 to 8.7.
- The biggest single-benchmark swing is Confabulations: 37.2% for GPT-4o mini and 19.1% for Qwen2.5 72B Instruct.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.40 / $5.60 for Qwen2.5 72B Instruct.
- 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-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 25.5 | 31.9 |
| Rank | 343 | 267 |
| Context | 128K | 131K |
| Input $/M | $0.15 | $1.40 |
| Output $/M | $0.60 | $5.60 |
| Weights | Proprietary | Open |

## Coding

- GPT-4o mini: 22.0 (#335)
- Qwen2.5 72B Instruct: 33.2 (#260)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| WeirdML | 11.8% | 16% |
| BigCodeBench Instruct | 46.1% | 45.8% |
| LMArena Coding | 1290 | 1292 |
| BigCodeBench Complete | 57.4% | 55.9% |
| Aider Polyglot | 3.6% | — |
| LiveBench Coding | 43.1% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |

## Agentic & Tool Use

- GPT-4o mini: 27.5 (#101)
- Qwen2.5 72B Instruct: 22.1 (#133)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| BALROG | 17.4% | 16.2% |
| TheAgentCompany | — | 5.7% |
| METR Time Horizons | — | 35.8% |

## Reasoning

- GPT-4o mini: 8.7 (#347)
- Qwen2.5 72B Instruct: 22.3 (#199)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Hard Prompts | 1267 | 1271 |
| DTBench | 54.4% | 62.9% |
| LMCA | 10.4% | 13.4% |
| Epoch Capabilities Index | 126.56 | 129 |
| PIQA | 88.7% | 82.6% |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| Mystery Game Puzzles | 12% | — |
| LiveBench Data Analysis | 50% | — |
| BIG-Bench Hard | — | 79.8% |
| ForecastBench | — | 57.5 |
| HellaSwag | — | 84.8% |
| LiveBench | 41.3% | — |
| WinoGrande | — | 82.3% |

## Math

- GPT-4o mini: 10.4 (#314)
- Qwen2.5 72B Instruct: 19.3 (#287)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 6.9% | 8.1% |
| Omni-MATH | 28% | 33% |
| LMArena Math | 1267 | 1283 |
| MATH Level 5 | 52.6% | 63.2% |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| LiveBench Math | 36.3% | — |
| GSM8K | 91.3% | — |

## Knowledge

- GPT-4o mini: 17.7 (#284)
- Qwen2.5 72B Instruct: 27.0 (#253)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| GPQA Diamond | 37.7% | 49.1% |
| MMLU-Pro | 60.3% | 63.1% |
| Confabulations | 37.2% | 19.1% |
| GPQA (HELM) | 36.8% | 42.6% |
| LMArena Expert | 1235 | 1245 |
| MMLU | 81.8% | 85.3% |
| SimpleQA Verified | 8.3% | — |
| ARC (AI2) Challenge | — | 94.5% |
| BoolQ | 88.7% | — |
| TriviaQA | — | 71.9% |

## Multimodal

- GPT-4o mini: 25.9 (#122)
- Qwen2.5 72B Instruct: —

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |

## Multilingual

- GPT-4o mini: 42.0 (#199)
- Qwen2.5 72B Instruct: 41.0 (#213)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Non-English | 1266 | 1252 |
| LMArena Chinese | 1265 | 1272 |
| LMArena French | 1297 | 1280 |
| LMArena German | 1272 | 1234 |
| LMArena Japanese | 1216 | 1180 |
| LMArena Korean | 1195 | 1188 |
| LMArena Russian | 1275 | 1264 |
| LMArena Spanish | 1276 | 1256 |

## Instruction Following

- GPT-4o mini: 61.9 (#239)
- Qwen2.5 72B Instruct: 65.5 (#221)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| IFEval | 78.2% | 80.6% |
| LMArena Instruction Following | 1258 | 1254 |
| LiveBench Instruction Following | 56.8% | — |

## Long Context

- GPT-4o mini: 39.1 (#186)
- Qwen2.5 72B Instruct: 38.9 (#188)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Longer Query | 1289 | 1282 |

## Writing & Preference

- GPT-4o mini: 39.5 (#248)
- Qwen2.5 72B Instruct: 46.7 (#215)

| Benchmark | GPT-4o mini | Qwen2.5 72B Instruct |
|---|---|---|
| LMArena Text | 1286 | 1269 |
| LMArena Creative Writing | 1268 | 1221 |
| WildBench | 79.1% | 80.2% |
| LMArena Multi-Turn | 1285 | 1272 |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| LiveBench Language | 28.6% | — |

## FAQ

### Is GPT-4o mini better than Qwen2.5 72B Instruct?

Qwen2.5 72B Instruct is the stronger model overall, scoring 31.9 to 25.5 on the Noometry Index. GPT-4o mini costs 9.3× less per token, which makes it the better buy when Qwen2.5 72B Instruct's lead doesn't matter for your workload.

### Which is cheaper, GPT-4o mini or Qwen2.5 72B Instruct?

GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen2.5 72B Instruct lists at $1.40 and $5.60.

### Is GPT-4o mini or Qwen2.5 72B Instruct better for coding?

Qwen2.5 72B Instruct scores higher on coding benchmarks: 33.2 versus 22.0 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-4o mini and Qwen2.5 72B Instruct share?

35 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Qwen2.5 72B Instruct has 43.