Model comparison
GPT-4 Turbo vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 30.5 on the Noometry Index.
Last verified . 31 shared benchmarks.
Summary
- They share 31 benchmarks with published results for both. GPT-4 Turbo scores higher in 0 categories and o4-mini in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where o4-mini leads 40.8 to 9.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 6.7% for GPT-4 Turbo and 81.7% for o4-mini.
- o4-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $10 / $30 for GPT-4 Turbo.
- o4-mini accepts more context: 200K tokens versus 128K.
Side by side
| GPT-4 Turbo | o4-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 30.5 | 41.6 |
| Released | 2023-11-06 | 2025-04-16 |
| 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 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
GPT-4 Turbo: 33.8 (#249), o4-mini: 40.9 (#127)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| WeirdML | 18% | 52.6% |
| LMArena Coding | 1268 | 1368 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| BigCodeBench Instruct | 48.2% | — |
| BigCodeBench Complete | 58.2% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
| HumanEval+ | 86.6% | — |
| MBPP+ | 73.3% | — |
Agentic & Tool Use Not comparable
GPT-4 Turbo: —, o4-mini: 32.6 (#61)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| METR Time Horizons | 36.7% | 63.9% |
| Berkeley Function Calling Leaderboard | — | 53.2% |
| GDPval | — | 25.3% |
Reasoning o4-mini leads
GPT-4 Turbo: 15.3 (#317), o4-mini: 24.6 (#162)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| SimpleBench | 25.1% | 38.7% |
| Chess Puzzles | 6% | 26% |
| LMArena Hard Prompts | 1251 | 1351 |
| DTBench | 61.6% | 77.6% |
| LMCA | 9.8% | 26.5% |
| Epoch Capabilities Index | 127.25 | 145.64 |
| ForecastBench | 59.4 | 61.8 |
| ARC-AGI-2 | — | 6.1% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| EnigmaEval | — | 9.2% |
| Mystery Game Puzzles | — | 5% |
Math o4-mini leads
GPT-4 Turbo: 9.0 (#322), o4-mini: 40.8 (#89)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | 36.1% |
| OTIS Mock AIME 2024-2025 | 6.7% | 81.7% |
| LMArena Math | 1272 | 1389 |
| MATH Level 5 | 46.7% | 97.8% |
| FrontierMath Tier 4 | — | 4.9% |
| Omni-MATH | — | 72% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
GPT-4 Turbo: 24.3 (#268), o4-mini: 43.6 (#91)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| GPQA Diamond | 46.6% | 79.6% |
| Confabulations | 28.4% | 15.8% |
| LMArena Expert | 1223 | 1343 |
| Humanity's Last Exam | — | 18.1% |
| SimpleQA Verified | — | 19.6% |
| MMLU-Pro | — | 82% |
| Vectara Hallucination Rate | — | 18.6% |
| GPQA (HELM) | — | 73.5% |
| MMLU | 81.3% | — |
Multimodal o4-mini leads
GPT-4 Turbo: 30.6 (#110), o4-mini: 40.2 (#49)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| LMArena Vision | 1090 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
GPT-4 Turbo: 40.5 (#216), o4-mini: 47.0 (#154)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| LMArena Non-English | 1245 | 1337 |
| LMArena Chinese | 1242 | 1354 |
| LMArena French | 1276 | 1364 |
| LMArena German | 1259 | 1336 |
| LMArena Japanese | 1194 | 1308 |
| LMArena Korean | 1187 | 1312 |
| LMArena Russian | 1259 | 1334 |
| LMArena Spanish | 1260 | 1347 |
Instruction Following o4-mini leads
GPT-4 Turbo: 65.8 (#216), o4-mini: 75.2 (#68)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| LMArena Instruction Following | 1249 | 1321 |
| IFEval | — | 92.8% |
Long Context o4-mini leads
GPT-4 Turbo: 38.0 (#206), o4-mini: 45.5 (#33)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| LMArena Longer Query | 1254 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
GPT-4 Turbo: 47.7 (#206), o4-mini: 54.0 (#152)
| Benchmark | GPT-4 Turbo | o4-mini |
|---|---|---|
| LMArena Text | 1272 | 1353 |
| LMArena Creative Writing | 1269 | 1294 |
| LMArena Multi-Turn | 1267 | 1350 |
| Short-Story Creative Writing | — | 75% |
| WildBench | — | 85.4% |
Frequently asked questions
Is GPT-4 Turbo better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 30.5 on the Noometry Index.
Which is cheaper, GPT-4 Turbo or o4-mini?
o4-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 o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 40.9 versus 33.8 in the Noometry coding category.
Which has the bigger context window?
o4-mini does, with 200K tokens against 128K.
How many benchmarks do GPT-4 Turbo and o4-mini share?
31 benchmarks have published results for both models. GPT-4 Turbo has 36 scored results on Noometry and o4-mini has 60.