Model comparison
GPT-5.3 Codex vs Step 2 16k Exp 202412
GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 38.6 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in coding, where GPT-5.3 Codex leads 48.5 to 37.9.
Side by side
| GPT-5.3 Codex | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 45.5 | 38.6 |
| Released | 2026-02-05 | — |
| Weights | Proprietary | Proprietary |
| Context window | 400K | — |
| Max output | 128K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 8 | 12 |
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: 48.5 (#51), Step 2 16k Exp 202412: 37.9 (#170)
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| SWE-bench Verified | 74.8% | — |
| LMArena WebDev | 1408 | — |
| WeirdML | 79.3% | — |
| LMArena Coding | — | 1316 |
| ALE-Bench | 1,655 | — |
Agentic & Tool Use Not comparable
GPT-5.3 Codex: 47.8 (#9), Step 2 16k Exp 202412: —
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| Terminal-Bench | 78.4% | — |
| METR Time Horizons | 74.5% | — |
| Vending-Bench 2 | 5,940 | — |
Reasoning Not comparable
GPT-5.3 Codex: —, Step 2 16k Exp 202412: 24.8 (#140)
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | — | 1299 |
| Epoch Capabilities Index | 156.84 | — |
Math Not comparable
GPT-5.3 Codex: —, Step 2 16k Exp 202412: 33.6 (#171)
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | — | 1305 |
Knowledge Not comparable
GPT-5.3 Codex: —, Step 2 16k Exp 202412: 34.6 (#187)
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | — | 1279 |
Multilingual Not comparable
GPT-5.3 Codex: —, Step 2 16k Exp 202412: 43.9 (#176)
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | — | 1290 |
| LMArena Chinese | — | 1331 |
| LMArena Russian | — | 1324 |
Instruction Following Not comparable
GPT-5.3 Codex: —, Step 2 16k Exp 202412: 68.1 (#187)
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | — | 1287 |
Long Context Not comparable
GPT-5.3 Codex: —, Step 2 16k Exp 202412: 39.7 (#165)
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | — | 1307 |
Writing & Preference Not comparable
GPT-5.3 Codex: —, Step 2 16k Exp 202412: 52.5 (#168)
| Benchmark | GPT-5.3 Codex | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | — | 1321 |
| LMArena Creative Writing | — | 1328 |
| LMArena Multi-Turn | — | 1292 |
Frequently asked questions
Is GPT-5.3 Codex better than Step 2 16k Exp 202412?
GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 38.6 on the Noometry Index.
Is GPT-5.3 Codex or Step 2 16k Exp 202412 better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.5 versus 37.9 in the Noometry coding category.
How many benchmarks do GPT-5.3 Codex and Step 2 16k Exp 202412 share?
0 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and Step 2 16k Exp 202412 has 12.