# GPT-5 Mini vs Qwen2.5-Coder-32B

> GPT-5 Mini is the stronger model overall, scoring 41.8 to 33.4 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-mini-vs-qwen2-5-coder-32b
- Last updated: 2026-10-11
- Shared benchmarks: 14

## Summary

- They share 14 benchmarks with published results for both. GPT-5 Mini scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5 Mini leads 40.1 to 22.6.
- The biggest single-benchmark swing is SWE-bench Verified (bash only): 59.8% for GPT-5 Mini and 9% for Qwen2.5-Coder-32B.
- GPT-5 Mini is cheaper at $0.25 / $2 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- GPT-5 Mini accepts more context: 400K tokens versus 33K.
- Qwen2.5-Coder-32B has downloadable open weights; the other is API-only.

## Snapshot

| | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 41.8 | 33.4 |
| Rank | 128 | 245 |
| Context | 400K | 33K |
| Input $/M | $0.25 | $0.66 |
| Output $/M | $2 | $1 |
| Weights | Proprietary | Open |

## Coding

- GPT-5 Mini: 40.1 (#146)
- Qwen2.5-Coder-32B: 22.6 (#333)

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| SWE-bench Verified (bash only) | 59.8% | 9% |
| LMArena Coding | 1406 | 1276 |
| SWE-bench Verified | 64.7% | — |
| Aider Polyglot | — | 16.4% |
| SWE-bench Multilingual | 39.7% | — |
| SciCode | 39.2% | — |
| WeirdML | 52.7% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 799.77 | — |
| AlgoTune | 1.38 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |

## Agentic & Tool Use

- GPT-5 Mini: 31.1 (#70)
- Qwen2.5-Coder-32B: —

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| Terminal-Bench | 34.8% | — |
| Berkeley Function Calling Leaderboard | 55.5% | — |
| Vending-Bench 2 | -31.18 | — |

## Reasoning

- GPT-5 Mini: 23.9 (#168)
- Qwen2.5-Coder-32B: 21.2 (#225)

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1380 | 1251 |
| Epoch Capabilities Index | 145.52 | 119.49 |
| ARC-AGI-2 | 4.4% | — |
| Kagi LLM Benchmark | 70.3% | — |
| ARC-AGI-1 | 54.3% | — |
| CritPt | 0% | — |
| Chess Puzzles | 30% | — |
| EnigmaEval | 8.2% | — |
| LiveBench Reasoning | — | 42.1% |
| Mystery Game Puzzles | 10% | — |
| DTBench | 80.5% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 34.2% | — |
| ForecastBench | 61 | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |

## Math

- GPT-5 Mini: 46.7 (#69)
- Qwen2.5-Coder-32B: 33.3 (#204)

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1378 | 1251 |
| FrontierMath (Tiers 1-3) | 46.7% | — |
| FrontierMath Tier 4 | 12.2% | — |
| OTIS Mock AIME 2024-2025 | 86.7% | — |
| ProofBench | 9% | — |
| Omni-MATH | 72.2% | — |
| LiveBench Math | — | 46.6% |
| MATH Level 5 | 97.8% | — |
| FrontierMath (Feb 2025 set) | 27.2% | — |
| FrontierMath Tier 4 (v1) | 6.3% | — |
| GSM8K | — | 93% |

## Knowledge

- GPT-5 Mini: 45.6 (#86)
- Qwen2.5-Coder-32B: 33.4 (#203)

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1379 | 1221 |
| GPQA Diamond | 75% | — |
| Humanity's Last Exam | 19.4% | — |
| SimpleQA Verified | 21.6% | — |
| MMLU-Pro | 83.5% | — |
| Confabulations | 13.3% | — |
| Vectara Hallucination Rate | 12.9% | — |
| GPQA (HELM) | 75.6% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |

## Multimodal

- GPT-5 Mini: 35.6 (#85)
- Qwen2.5-Coder-32B: —

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1202 | — |
| VPCT | 40.2% | — |

## Multilingual

- GPT-5 Mini: 48.9 (#137)
- Qwen2.5-Coder-32B: 37.8 (#235)

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1363 | 1205 |
| LMArena Chinese | 1385 | 1222 |
| LMArena Russian | 1362 | 1228 |
| LMArena French | 1386 | — |
| LMArena German | 1366 | — |
| LMArena Japanese | 1341 | — |
| LMArena Korean | 1308 | — |
| LMArena Spanish | 1355 | — |

## Instruction Following

- GPT-5 Mini: 76.2 (#46)
- Qwen2.5-Coder-32B: 61.4 (#245)

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1357 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
| IFEval | 92.7% | — |

## Long Context

- GPT-5 Mini: 41.9 (#132)
- Qwen2.5-Coder-32B: 38.0 (#208)

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1355 | 1251 |
| Fiction.LiveBench | 69.4% | — |

## Writing & Preference

- GPT-5 Mini: 55.2 (#148)
- Qwen2.5-Coder-32B: 41.6 (#240)

| Benchmark | GPT-5 Mini | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1373 | 1230 |
| LMArena Creative Writing | 1325 | 1174 |
| LMArena Multi-Turn | 1363 | 1222 |
| Short-Story Creative Writing | 83.1% | — |
| EQ-Bench Creative Writing | 1313 | — |
| WildBench | 85.5% | — |
| LiveBench Language | — | 23.3% |

## FAQ

### Is GPT-5 Mini better than Qwen2.5-Coder-32B?

GPT-5 Mini is the stronger model overall, scoring 41.8 to 33.4 on the Noometry Index.

### Which is cheaper, GPT-5 Mini or Qwen2.5-Coder-32B?

GPT-5 Mini is cheaper. It lists at $0.25 per million input tokens and $2 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.

### Is GPT-5 Mini or Qwen2.5-Coder-32B better for coding?

GPT-5 Mini scores higher on coding benchmarks: 40.1 versus 22.6 in the Noometry coding category.

### Which has the bigger context window?

GPT-5 Mini does, with 400K tokens against 33K.

### How many benchmarks do GPT-5 Mini and Qwen2.5-Coder-32B share?

14 benchmarks have published results for both models. GPT-5 Mini has 60 scored results on Noometry and Qwen2.5-Coder-32B has 31.