Model comparison
GPT-5.4 mini vs Qwen2.5 32B Instruct
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 30.1 on the Noometry Index.
Last verified . 4 shared benchmarks.
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. GPT-5.4 mini scores higher in 4 categories and Qwen2.5 32B Instruct in 0 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.4 mini leads 45.5 to 16.2.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 88.9% for GPT-5.4 mini and 7.4% for Qwen2.5 32B Instruct.
- Qwen2.5 32B Instruct is cheaper at $0.70 / $2.80 per million input/output tokens, against $0.75 / $4.50 for GPT-5.4 mini.
- GPT-5.4 mini accepts more context: 400K tokens versus 131K.
- Qwen2.5 32B Instruct has downloadable open weights; the other is API-only.
Side by side
| GPT-5.4 mini | Qwen2.5 32B Instruct | |
|---|---|---|
| Provider | OpenAI | Alibaba (Qwen) |
| Noometry Index | 45.0 | 30.1 |
| Released | 2026-03-17 | 2024-09 |
| Weights | Proprietary | Open |
| Context window | 400K | 131K |
| Max output | 128K | 8K |
| Input $ / M tokens | $0.75 | $0.70 |
| Output $ / M tokens | $4.50 | $2.80 |
| Results tracked | 46 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-5.4 mini: 45.2 (#72), Qwen2.5 32B Instruct: 38.7 (#169)
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| FrontierCode | 27% | — |
| LMArena WebDev | 1397 | — |
| SciCode | 49.9% | — |
| WeirdML | 60.3% | — |
| BigCodeBench Instruct | — | 45% |
| LMArena Coding | 1438 | — |
| BigCodeBench Complete | — | 52.3% |
| ALE-Bench | 1,189 | — |
Agentic & Tool Use Not comparable
GPT-5.4 mini: 29.9 (#81), Qwen2.5 32B Instruct: —
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| DeepResearch Bench | 36.3% | — |
Reasoning GPT-5.4 mini leads
GPT-5.4 mini: 30.4 (#85), Qwen2.5 32B Instruct: 19.2 (#266)
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| Chess Puzzles | 24% | 0% |
| Epoch Capabilities Index | 148.84 | 128.52 |
| ARC-AGI-2 | 18.9% | — |
| Kagi LLM Benchmark | 37.9% | — |
| NYT Connections (extended) | 61.8% | — |
| ARC-AGI-1 | 63.7% | — |
| CritPt | 10% | — |
| Thematic Generalization | 61.7% | — |
| LMArena Hard Prompts | 1424 | — |
| Mystery Game Puzzles | 11% | — |
| DTBench | 80% | — |
| LMCA | 40.8% | — |
| ForecastBench | 57 | — |
Math GPT-5.4 mini leads
GPT-5.4 mini: 45.5 (#75), Qwen2.5 32B Instruct: 16.2 (#296)
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 88.9% | 7.4% |
| FrontierMath (Tiers 1-3) | 51.2% | — |
| FrontierMath Tier 4 | 9.8% | — |
| ProofBench | 21% | — |
| LMArena Math | 1419 | — |
| MATH Level 5 | — | 56.1% |
| FrontierMath (Feb 2025 set) | 28.3% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge GPT-5.4 mini leads
GPT-5.4 mini: 51.5 (#67), Qwen2.5 32B Instruct: 24.9 (#266)
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| GPQA Diamond | 86.9% | 46.1% |
| SimpleQA Verified | 29.4% | — |
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1435 | — |
Multimodal Not comparable
GPT-5.4 mini: 39.7 (#56), Qwen2.5 32B Instruct: —
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Vision | 1245 | — |
Multilingual Not comparable
GPT-5.4 mini: 51.9 (#96), Qwen2.5 32B Instruct: —
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Non-English | 1405 | — |
| LMArena Chinese | 1446 | — |
| LMArena French | 1440 | — |
| LMArena German | 1409 | — |
| LMArena Japanese | 1374 | — |
| LMArena Korean | 1368 | — |
| LMArena Russian | 1417 | — |
| LMArena Spanish | 1405 | — |
Instruction Following Not comparable
GPT-5.4 mini: 74.1 (#102), Qwen2.5 32B Instruct: —
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Instruction Following | 1405 | — |
Long Context Not comparable
GPT-5.4 mini: 43.0 (#112), Qwen2.5 32B Instruct: —
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Longer Query | 1407 | — |
Writing & Preference Not comparable
GPT-5.4 mini: 64.0 (#58), Qwen2.5 32B Instruct: —
| Benchmark | GPT-5.4 mini | Qwen2.5 32B Instruct |
|---|---|---|
| LMArena Text | 1412 | — |
| LMArena Creative Writing | 1370 | — |
| EQ-Bench Creative Writing | 1665 | — |
| LMArena Multi-Turn | 1429 | — |
Frequently asked questions
Is GPT-5.4 mini better than Qwen2.5 32B Instruct?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 30.1 on the Noometry Index.
Which is cheaper, GPT-5.4 mini or Qwen2.5 32B Instruct?
Qwen2.5 32B Instruct is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-5.4 mini or Qwen2.5 32B Instruct better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 38.7 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 131K.
How many benchmarks do GPT-5.4 mini and Qwen2.5 32B Instruct share?
4 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Qwen2.5 32B Instruct has 7.