Model comparison
GPT-4 Turbo vs GPT-4o mini
GPT-4 Turbo is the stronger model overall, scoring 30.5 to 25.5 on the Noometry Index. GPT-4o mini costs 57× less per token, which makes it the better buy when GPT-4 Turbo's lead doesn't matter for your workload.
Last verified . 34 shared benchmarks.
Summary
- They share 34 benchmarks with published results for both. GPT-4 Turbo scores higher in 6 categories and GPT-4o mini in 3 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-4 Turbo leads 33.8 to 22.0.
- The biggest single-benchmark swing is SimpleBench: 25.1% for GPT-4 Turbo and 10.7% for GPT-4o mini.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
Side by side
| GPT-4 Turbo | GPT-4o mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 30.5 | 25.5 |
| Released | 2023-11-06 | 2024-07-18 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 128K |
| Max output | 4K | 16K |
| Input $ / M tokens | $10 | $0.15 |
| Output $ / M tokens | $30 | $0.60 |
| Results tracked | 36 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-4 Turbo leads
GPT-4 Turbo: 33.8 (#249), GPT-4o mini: 22.0 (#335)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| WeirdML | 18% | 11.8% |
| BigCodeBench Instruct | 48.2% | 46.1% |
| LMArena Coding | 1268 | 1290 |
| BigCodeBench Complete | 58.2% | 57.4% |
| HumanEval+ | 86.6% | 83.5% |
| MBPP+ | 73.3% | 72.2% |
| Aider Polyglot | — | 3.6% |
| LiveBench Coding | — | 43.1% |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, GPT-4o mini: 27.5 (#101)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| BALROG | — | 17.4% |
| METR Time Horizons | 36.7% | — |
Reasoning GPT-4 Turbo leads
GPT-4 Turbo: 15.3 (#317), GPT-4o mini: 8.7 (#347)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| SimpleBench | 25.1% | 10.7% |
| Chess Puzzles | 6% | 0% |
| LMArena Hard Prompts | 1251 | 1267 |
| DTBench | 61.6% | 54.4% |
| LMCA | 9.8% | 10.4% |
| Epoch Capabilities Index | 127.25 | 126.56 |
| ARC-AGI-2 | — | 0% |
| Kagi LLM Benchmark | — | 28.8% |
| LiveBench Reasoning | — | 32.8% |
| Mystery Game Puzzles | — | 12% |
| LiveBench Data Analysis | — | 50% |
| ForecastBench | 59.4 | — |
| LiveBench | — | 41.3% |
| PIQA | — | 88.7% |
Math GPT-4o mini leads
GPT-4 Turbo: 9.0 (#322), GPT-4o mini: 10.4 (#314)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 0.7% |
| OTIS Mock AIME 2024-2025 | 6.7% | 6.9% |
| LMArena Math | 1272 | 1267 |
| MATH Level 5 | 46.7% | 52.6% |
| Omni-MATH | — | 28% |
| LiveBench Math | — | 36.3% |
| GSM8K | — | 91.3% |
Knowledge GPT-4 Turbo leads
GPT-4 Turbo: 24.3 (#268), GPT-4o mini: 17.7 (#284)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| GPQA Diamond | 46.6% | 37.7% |
| Confabulations | 28.4% | 37.2% |
| LMArena Expert | 1223 | 1235 |
| MMLU | 81.3% | 81.8% |
| SimpleQA Verified | — | 8.3% |
| MMLU-Pro | — | 60.3% |
| GPQA (HELM) | — | 36.8% |
| BoolQ | — | 88.7% |
Multimodal GPT-4 Turbo leads
GPT-4 Turbo: 30.6 (#110), GPT-4o mini: 25.9 (#122)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| LMArena Vision | 1090 | 1066 |
| Video-MME | — | 64.8% |
| GeoBench | — | 64% |
| VPCT | — | 34% |
Multilingual GPT-4o mini leads
GPT-4 Turbo: 40.5 (#216), GPT-4o mini: 42.0 (#199)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| LMArena Non-English | 1245 | 1266 |
| LMArena Chinese | 1242 | 1265 |
| LMArena French | 1276 | 1297 |
| LMArena German | 1259 | 1272 |
| LMArena Japanese | 1194 | 1216 |
| LMArena Korean | 1187 | 1195 |
| LMArena Russian | 1259 | 1275 |
| LMArena Spanish | 1260 | 1276 |
Instruction Following GPT-4 Turbo leads
GPT-4 Turbo: 65.8 (#216), GPT-4o mini: 61.9 (#239)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| LMArena Instruction Following | 1249 | 1258 |
| LiveBench Instruction Following | — | 56.8% |
| IFEval | — | 78.2% |
Long Context GPT-4o mini leads
GPT-4 Turbo: 38.0 (#206), GPT-4o mini: 39.1 (#186)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| LMArena Longer Query | 1254 | 1289 |
Writing & Preference GPT-4 Turbo leads
GPT-4 Turbo: 47.7 (#206), GPT-4o mini: 39.5 (#248)
| Benchmark | GPT-4 Turbo | GPT-4o mini |
|---|---|---|
| LMArena Text | 1272 | 1286 |
| LMArena Creative Writing | 1269 | 1268 |
| LMArena Multi-Turn | 1267 | 1285 |
| Short-Story Creative Writing | — | 67.2% |
| EQ-Bench Creative Writing | — | 873 |
| WildBench | — | 79.1% |
| LiveBench Language | — | 28.6% |
Frequently asked questions
Is GPT-4 Turbo better than GPT-4o mini?
GPT-4 Turbo is the stronger model overall, scoring 30.5 to 25.5 on the Noometry Index. GPT-4o mini costs 57× less per token, which makes it the better buy when GPT-4 Turbo's lead doesn't matter for your workload.
Which is cheaper, GPT-4 Turbo or GPT-4o mini?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or GPT-4o mini better for coding?
GPT-4 Turbo scores higher on coding benchmarks: 33.8 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do GPT-4 Turbo and GPT-4o mini share?
34 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and GPT-4o mini has 60.