# GPT-4o mini vs Qwen2.5-Max

> Qwen2.5-Max is the stronger model overall, scoring 40.1 to 25.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-4o-mini-vs-qwen2-5-max
- Last updated: 2026-10-10
- Shared benchmarks: 27

## Summary

- They share 27 benchmarks with published results for both. GPT-4o mini scores higher in 0 categories and Qwen2.5-Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen2.5-Max leads 34.3 to 9.9.
- The biggest single-benchmark swing is LiveBench Language: 28.6% for GPT-4o mini and 56.3% for Qwen2.5-Max.

## Snapshot

| | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 25.4 | 40.1 |
| Rank | 337 | 142 |
| Context | 128K | — |
| Input $/M | $0.15 | — |
| Output $/M | $0.60 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-4o mini: 21.6 (#330)
- Qwen2.5-Max: 41.2 (#118)

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| LiveBench Coding | 43.1% | 64.4% |
| LMArena Coding | 1290 | 1359 |
| Aider Polyglot | 3.6% | — |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| BigCodeBench Complete | 57.4% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |

## Agentic & Tool Use

- GPT-4o mini: 27.2 (#95)
- Qwen2.5-Max: —

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| BALROG | 17.4% | — |

## Reasoning

- GPT-4o mini: 8.7 (#343)
- Qwen2.5-Max: 24.6 (#144)

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| LiveBench Reasoning | 32.8% | 51.4% |
| LMArena Hard Prompts | 1267 | 1360 |
| LiveBench Data Analysis | 50% | 67.9% |
| Epoch Capabilities Index | 126.56 | 132.54 |
| LiveBench | 41.3% | 62.3% |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | 0% | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LMCA | 10.4% | — |
| PIQA | 88.7% | — |

## Math

- GPT-4o mini: 9.9 (#307)
- Qwen2.5-Max: 34.3 (#162)

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| LiveBench Math | 36.3% | 58.4% |
| LMArena Math | 1267 | 1369 |
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| Omni-MATH | 28% | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |

## Knowledge

- GPT-4o mini: 17.7 (#279)
- Qwen2.5-Max: 34.8 (#181)

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| Confabulations | 37.2% | 21.8% |
| LMArena Expert | 1235 | 1337 |
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| GPQA (HELM) | 36.8% | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |

## Multimodal

- GPT-4o mini: 25.3 (#117)
- Qwen2.5-Max: —

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

## Multilingual

- GPT-4o mini: 42.2 (#194)
- Qwen2.5-Max: 48.3 (#140)

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1266 | 1352 |
| LMArena Chinese | 1264 | 1382 |
| LMArena French | 1296 | 1396 |
| LMArena German | 1272 | 1350 |
| LMArena Japanese | 1216 | 1299 |
| LMArena Korean | 1195 | 1304 |
| LMArena Russian | 1275 | 1353 |
| LMArena Spanish | 1276 | 1377 |

## Instruction Following

- GPT-4o mini: 62.1 (#234)
- Qwen2.5-Max: 71.5 (#147)

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| LiveBench Instruction Following | 56.8% | 75.3% |
| LMArena Instruction Following | 1259 | 1335 |
| IFEval | 78.2% | — |

## Long Context

- GPT-4o mini: 39.1 (#181)
- Qwen2.5-Max: 41.3 (#137)

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1289 | 1358 |

## Writing & Preference

- GPT-4o mini: 39.7 (#243)
- Qwen2.5-Max: 55.6 (#141)

| Benchmark | GPT-4o mini | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1286 | 1367 |
| LMArena Creative Writing | 1268 | 1339 |
| Short-Story Creative Writing | 67.2% | 72.9% |
| LMArena Multi-Turn | 1285 | 1364 |
| LiveBench Language | 28.6% | 56.3% |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |

## FAQ

### Is GPT-4o mini better than Qwen2.5-Max?

Qwen2.5-Max is the stronger model overall, scoring 40.1 to 25.4 on the Noometry Index.

### Is GPT-4o mini or Qwen2.5-Max better for coding?

Qwen2.5-Max scores higher on coding benchmarks: 41.2 versus 21.6 in the Noometry coding category.

### How many benchmarks do GPT-4o mini and Qwen2.5-Max share?

27 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and Qwen2.5-Max has 27.