Model comparison
GPT-4o mini vs GPT-5.2 Codex
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 25.5 on the Noometry Index. GPT-4o mini costs 18× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
Summary
- The widest gap is in coding, where GPT-5.2 Codex leads 45.5 to 22.0.
- GPT-4o mini is cheaper at $0.15 / $0.60 per million input/output tokens, against $1.75 / $14 for GPT-5.2 Codex.
- GPT-5.2 Codex accepts more context: 400K tokens versus 128K.
Side by side
| GPT-4o mini | GPT-5.2 Codex | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 25.5 | 42.6 |
| Released | 2024-07-18 | 2025-12-18 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 400K |
| Max output | 16K | 128K |
| Input $ / M tokens | $0.15 | $1.75 |
| Output $ / M tokens | $0.60 | $14 |
| Results tracked | 60 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.2 Codex leads
GPT-4o mini: 22.0 (#335), GPT-5.2 Codex: 45.5 (#71)
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| SWE-bench Verified (bash only) | — | 72.8% |
| Aider Polyglot | 3.6% | — |
| LMArena WebDev | — | 1339 |
| SWE-bench Multilingual | — | 66.3% |
| WeirdML | 11.8% | — |
| BigCodeBench Instruct | 46.1% | — |
| LiveBench Coding | 43.1% | — |
| LMArena Coding | 1290 | — |
| BigCodeBench Complete | 57.4% | — |
| ALE-Bench | — | 1,300 |
| HumanEval+ | 83.5% | — |
| MBPP+ | 72.2% | — |
Agentic & Tool Use GPT-5.2 Codex leads
GPT-4o mini: 27.5 (#101), GPT-5.2 Codex: 41.0 (#22)
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| Terminal-Bench | — | 66.5% |
| BALROG | 17.4% | — |
Reasoning Not comparable
GPT-4o mini: 8.7 (#347), GPT-5.2 Codex: —
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| ARC-AGI-2 | 0% | — |
| SimpleBench | 10.7% | — |
| Kagi LLM Benchmark | 28.8% | — |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | 32.8% | — |
| LMArena Hard Prompts | 1267 | — |
| Mystery Game Puzzles | 12% | — |
| DTBench | 54.4% | — |
| LiveBench Data Analysis | 50% | — |
| LMCA | 10.4% | — |
| Epoch Capabilities Index | 126.56 | — |
| LiveBench | 41.3% | — |
| PIQA | 88.7% | — |
Math Not comparable
GPT-4o mini: 10.4 (#314), GPT-5.2 Codex: —
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 0.7% | — |
| OTIS Mock AIME 2024-2025 | 6.9% | — |
| Omni-MATH | 28% | — |
| LiveBench Math | 36.3% | — |
| LMArena Math | 1267 | — |
| MATH Level 5 | 52.6% | — |
| GSM8K | 91.3% | — |
Knowledge Not comparable
GPT-4o mini: 17.7 (#284), GPT-5.2 Codex: —
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| GPQA Diamond | 37.7% | — |
| SimpleQA Verified | 8.3% | — |
| MMLU-Pro | 60.3% | — |
| Confabulations | 37.2% | — |
| GPQA (HELM) | 36.8% | — |
| LMArena Expert | 1235 | — |
| BoolQ | 88.7% | — |
| MMLU | 81.8% | — |
Multimodal Not comparable
GPT-4o mini: 25.9 (#122), GPT-5.2 Codex: —
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| LMArena Vision | 1066 | — |
| Video-MME | 64.8% | — |
| GeoBench | 64% | — |
| VPCT | 34% | — |
Multilingual Not comparable
GPT-4o mini: 42.0 (#199), GPT-5.2 Codex: —
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| LMArena Non-English | 1266 | — |
| LMArena Chinese | 1265 | — |
| LMArena French | 1297 | — |
| LMArena German | 1272 | — |
| LMArena Japanese | 1216 | — |
| LMArena Korean | 1195 | — |
| LMArena Russian | 1275 | — |
| LMArena Spanish | 1276 | — |
Instruction Following Not comparable
GPT-4o mini: 61.9 (#239), GPT-5.2 Codex: —
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| LiveBench Instruction Following | 56.8% | — |
| IFEval | 78.2% | — |
| LMArena Instruction Following | 1258 | — |
Long Context Not comparable
GPT-4o mini: 39.1 (#186), GPT-5.2 Codex: —
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| LMArena Longer Query | 1289 | — |
Writing & Preference Not comparable
GPT-4o mini: 39.5 (#248), GPT-5.2 Codex: —
| Benchmark | GPT-4o mini | GPT-5.2 Codex |
|---|---|---|
| LMArena Text | 1286 | — |
| LMArena Creative Writing | 1268 | — |
| Short-Story Creative Writing | 67.2% | — |
| EQ-Bench Creative Writing | 873 | — |
| WildBench | 79.1% | — |
| LMArena Multi-Turn | 1285 | — |
| LiveBench Language | 28.6% | — |
Frequently asked questions
Is GPT-4o mini better than GPT-5.2 Codex?
GPT-5.2 Codex is the stronger model overall, scoring 42.6 to 25.5 on the Noometry Index. GPT-4o mini costs 18× less per token, which makes it the better buy when GPT-5.2 Codex's lead doesn't matter for your workload.
Which is cheaper, GPT-4o mini or GPT-5.2 Codex?
GPT-4o mini is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; GPT-5.2 Codex lists at $1.75 and $14.
Is GPT-4o mini or GPT-5.2 Codex better for coding?
GPT-5.2 Codex scores higher on coding benchmarks: 45.5 versus 22.0 in the Noometry coding category.
Which has the bigger context window?
GPT-5.2 Codex does, with 400K tokens against 128K.
How many benchmarks do GPT-4o mini and GPT-5.2 Codex share?
0 benchmarks have published results for both models. GPT-4o mini has 60 scored results on Noometry and GPT-5.2 Codex has 5.