Model comparison
GPT-3.5-turbo vs GPT-5.4 mini
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 2.3× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
Summary
- They share 28 benchmarks with published results for both. GPT-3.5-turbo scores higher in 0 categories and GPT-5.4 mini in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where GPT-5.4 mini leads 51.5 to 10.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.2% for GPT-3.5-turbo and 88.9% for GPT-5.4 mini.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 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 16K.
Side by side
| GPT-3.5-turbo | GPT-5.4 mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 23.2 | 45.0 |
| Released | 2023-03-01 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 16K | 400K |
| Max output | 4K | 128K |
| Input $ / M tokens | $0.50 | $0.75 |
| Output $ / M tokens | $1.50 | $4.50 |
| Results tracked | 44 | 46 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 mini leads
GPT-3.5-turbo: 23.9 (#331), GPT-5.4 mini: 45.2 (#72)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| WeirdML | 3.5% | 60.3% |
| LMArena Coding | 1136 | 1438 |
| FrontierCode | — | 27% |
| LMArena WebDev | — | 1397 |
| SciCode | — | 49.9% |
| BigCodeBench Instruct | 39.1% | — |
| BigCodeBench Complete | 50.6% | — |
| ALE-Bench | — | 1,189 |
| HumanEval+ | 70.7% | — |
| MBPP+ | 69.7% | — |
Agentic & Tool Use Not comparable
GPT-3.5-turbo: —, GPT-5.4 mini: 29.9 (#81)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| DeepResearch Bench | — | 36.3% |
| METR Time Horizons | 21.5% | — |
Reasoning GPT-5.4 mini leads
GPT-3.5-turbo: 13.8 (#332), GPT-5.4 mini: 30.4 (#85)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| Chess Puzzles | 0% | 24% |
| LMArena Hard Prompts | 1108 | 1424 |
| Mystery Game Puzzles | 3% | 11% |
| DTBench | 48.5% | 80% |
| LMCA | 9.7% | 40.8% |
| Epoch Capabilities Index | 118.55 | 148.84 |
| ForecastBench | 50.4 | 57 |
| 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% |
| Adversarial NLI | 58.1% | — |
| BIG-Bench Hard | 61.6% | — |
| CommonsenseQA 2.0 | 57% | — |
| WinoGrande | 81.6% | — |
Math GPT-5.4 mini leads
GPT-3.5-turbo: 6.3 (#327), GPT-5.4 mini: 45.5 (#75)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0% | 51.2% |
| OTIS Mock AIME 2024-2025 | 2.2% | 88.9% |
| LMArena Math | 1142 | 1419 |
| FrontierMath Tier 4 | — | 9.8% |
| ProofBench | — | 21% |
| MATH Level 5 | 15.9% | — |
| FrontierMath (Feb 2025 set) | — | 28.3% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
| GSM8K | 57.8% | — |
Knowledge GPT-5.4 mini leads
GPT-3.5-turbo: 10.0 (#303), GPT-5.4 mini: 51.5 (#67)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| GPQA Diamond | 28% | 86.9% |
| LMArena Expert | 1070 | 1435 |
| SimpleQA Verified | — | 29.4% |
| Vectara Hallucination Rate | — | 5.5% |
| ARC (AI2) Challenge | 87.4% | — |
| BoolQ | 87% | — |
| MMLU | 71.4% | — |
| OpenBookQA | 86% | — |
| TriviaQA | 85.8% | — |
Multimodal Not comparable
GPT-3.5-turbo: —, GPT-5.4 mini: 39.7 (#56)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Vision | — | 1245 |
Multilingual GPT-5.4 mini leads
GPT-3.5-turbo: 31.5 (#258), GPT-5.4 mini: 51.9 (#96)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Non-English | 1108 | 1405 |
| LMArena Chinese | 1075 | 1446 |
| LMArena French | 1118 | 1440 |
| LMArena German | 1090 | 1409 |
| LMArena Japanese | 1043 | 1374 |
| LMArena Korean | 1019 | 1368 |
| LMArena Russian | 1123 | 1417 |
| LMArena Spanish | 1121 | 1405 |
Instruction Following GPT-5.4 mini leads
GPT-3.5-turbo: 57.9 (#262), GPT-5.4 mini: 74.1 (#102)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Instruction Following | 1119 | 1405 |
Long Context GPT-5.4 mini leads
GPT-3.5-turbo: 34.0 (#254), GPT-5.4 mini: 43.0 (#112)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Longer Query | 1121 | 1407 |
Writing & Preference GPT-5.4 mini leads
GPT-3.5-turbo: 25.3 (#305), GPT-5.4 mini: 64.0 (#58)
| Benchmark | GPT-3.5-turbo | GPT-5.4 mini |
|---|---|---|
| LMArena Text | 1125 | 1412 |
| LMArena Creative Writing | 1092 | 1370 |
| EQ-Bench Creative Writing | 451 | 1665 |
| LMArena Multi-Turn | 1117 | 1429 |
Frequently asked questions
Is GPT-3.5-turbo better than GPT-5.4 mini?
GPT-5.4 mini is the stronger model overall, scoring 45.0 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 2.3× less per token, which makes it the better buy when GPT-5.4 mini's lead doesn't matter for your workload.
Which is cheaper, GPT-3.5-turbo or GPT-5.4 mini?
GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; GPT-5.4 mini lists at $0.75 and $4.50.
Is GPT-3.5-turbo or GPT-5.4 mini better for coding?
GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 mini does, with 400K tokens against 16K.
How many benchmarks do GPT-3.5-turbo and GPT-5.4 mini share?
28 benchmarks have published results for both models. GPT-3.5-turbo has 44 scored results on Noometry and GPT-5.4 mini has 46.