Model comparison
GPT-4 Turbo vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 30.5 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. GPT-4 Turbo scores higher in 1 category and o3-mini in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where o3-mini leads 28.1 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 76.9% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- o3-mini accepts more context: 200K tokens versus 128K.
Side by side
| GPT-4 Turbo | o3-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 30.5 | 36.7 |
| Released | 2023-11-06 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 200K |
| Max output | 4K | 100K |
| Input $ / M tokens | $10 | $1.10 |
| Output $ / M tokens | $30 | $4.40 |
| Results tracked | 36 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
GPT-4 Turbo: 33.8 (#249), o3-mini: 40.8 (#132)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| WeirdML | 18% | 43.7% |
| LMArena Coding | 1268 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| BigCodeBench Instruct | 48.2% | — |
| LiveBench Coding | — | 82.7% |
| BigCodeBench Complete | 58.2% | — |
| CadEval | — | 54% |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, o3-mini: 29.6 (#84)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
| METR Time Horizons | 36.7% | — |
Reasoning Too close to call
GPT-4 Turbo: 15.3 (#317), o3-mini: 16.3 (#305)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| SimpleBench | 25.1% | 22.8% |
| Chess Puzzles | 6% | 17% |
| LMArena Hard Prompts | 1251 | 1366 |
| DTBench | 61.6% | 68.8% |
| LMCA | 9.8% | 19% |
| Epoch Capabilities Index | 127.25 | 140.34 |
| ForecastBench | 59.4 | 59.6 |
| ARC-AGI-2 | — | 3% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| LiveBench Data Analysis | — | 70.6% |
| LiveBench | — | 75.9% |
Math o3-mini leads
GPT-4 Turbo: 9.0 (#322), o3-mini: 28.1 (#244)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 18.6% |
| OTIS Mock AIME 2024-2025 | 6.7% | 76.9% |
| LMArena Math | 1272 | 1396 |
| MATH Level 5 | 46.7% | 96.5% |
| FrontierMath Tier 4 | — | 0% |
| LiveBench Math | — | 77.3% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
GPT-4 Turbo: 24.3 (#268), o3-mini: 38.3 (#146)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| GPQA Diamond | 46.6% | 77% |
| Confabulations | 28.4% | 17.9% |
| LMArena Expert | 1223 | 1364 |
| SimpleQA Verified | — | 15.3% |
| MMLU | 81.3% | — |
Multimodal Not comparable
GPT-4 Turbo: 30.6 (#110), o3-mini: —
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| LMArena Vision | 1090 | — |
Multilingual o3-mini leads
GPT-4 Turbo: 40.5 (#216), o3-mini: 45.7 (#164)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| LMArena Non-English | 1245 | 1319 |
| LMArena Chinese | 1242 | 1379 |
| LMArena French | 1276 | 1334 |
| LMArena German | 1259 | 1303 |
| LMArena Japanese | 1194 | 1286 |
| LMArena Korean | 1187 | 1314 |
| LMArena Russian | 1259 | 1304 |
| LMArena Spanish | 1260 | 1321 |
Instruction Following o3-mini leads
GPT-4 Turbo: 65.8 (#216), o3-mini: 75.1 (#72)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1249 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context GPT-4 Turbo leads
GPT-4 Turbo: 38.0 (#206), o3-mini: 33.8 (#256)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| LMArena Longer Query | 1254 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
GPT-4 Turbo: 47.7 (#206), o3-mini: 50.3 (#182)
| Benchmark | GPT-4 Turbo | o3-mini |
|---|---|---|
| LMArena Text | 1272 | 1337 |
| LMArena Creative Writing | 1269 | 1286 |
| LMArena Multi-Turn | 1267 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is GPT-4 Turbo better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 30.5 on the Noometry Index.
Which is cheaper, GPT-4 Turbo or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; GPT-4 Turbo lists at $10 and $30.
Is GPT-4 Turbo or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
o3-mini does, with 200K tokens against 128K.
How many benchmarks do GPT-4 Turbo and o3-mini share?
29 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and o3-mini has 51.