Model comparison
GPT-5.3 Codex vs o1-mini
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 34.0 on the Noometry Index.
Last verified . 2 shared benchmarks.
Summary
- They share 2 benchmarks with published results for both. GPT-5.3 Codex scores higher in 2 categories and o1-mini in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 24.6.
- The biggest single-benchmark swing is WeirdML: 79.3% for GPT-5.3 Codex and 36.3% for o1-mini.
Side by side
| GPT-5.3 Codex | o1-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 45.8 | 34.0 |
| Released | 2026-02-05 | 2024-09-12 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 8 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
GPT-5.3 Codex: 48.6 (#56), o1-mini: 35.5 (#224)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| WeirdML | 79.3% | 36.3% |
| SWE-bench Verified | 74.8% | — |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1409 | — |
| LiveBench Coding | — | 48% |
| LMArena Coding | — | 1362 |
| ALE-Bench | 1,655 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use GPT-5.3 Codex leads
GPT-5.3 Codex: 48.0 (#9), o1-mini: 24.6 (#118)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| Cybench | — | 10% |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, o1-mini: 8.8 (#346)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| Epoch Capabilities Index | 156.77 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| LMArena Hard Prompts | — | 1333 |
| LiveBench Data Analysis | — | 57.9% |
| LiveBench | — | 57.8% |
Math Not comparable
GPT-5.3 Codex: —, o1-mini: 35.4 (#186)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| LiveBench Math | — | 62% |
| LMArena Math | — | 1358 |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Not comparable
GPT-5.3 Codex: —, o1-mini: 34.9 (#192)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| LMArena Expert | — | 1316 |
Multilingual Not comparable
GPT-5.3 Codex: —, o1-mini: 43.6 (#182)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| LMArena Non-English | — | 1289 |
| LMArena Chinese | — | 1314 |
| LMArena French | — | 1293 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
| LMArena Russian | — | 1283 |
| LMArena Spanish | — | 1303 |
Instruction Following Not comparable
GPT-5.3 Codex: —, o1-mini: 66.7 (#206)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| LiveBench Instruction Following | — | 65.4% |
| LMArena Instruction Following | — | 1304 |
Long Context Not comparable
GPT-5.3 Codex: —, o1-mini: 40.1 (#161)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| LMArena Longer Query | — | 1320 |
Writing & Preference Not comparable
GPT-5.3 Codex: —, o1-mini: 48.4 (#202)
| Benchmark | GPT-5.3 Codex | o1-mini |
|---|---|---|
| LMArena Text | — | 1317 |
| LMArena Creative Writing | — | 1244 |
| Short-Story Creative Writing | — | 64.9% |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is GPT-5.3 Codex better than o1-mini?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 34.0 on the Noometry Index.
Is GPT-5.3 Codex or o1-mini better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 35.5 in the Noometry coding category.
How many benchmarks do GPT-5.3 Codex and o1-mini share?
2 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and o1-mini has 39.