Model comparison
GPT-5.3 Chat vs GPT-5-Codex
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 37.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
Summary
- GPT-5-Codex is cheaper at $1.25 / $10 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.
- GPT-5-Codex accepts more context: 400K tokens versus 128K.
Side by side
| GPT-5.3 Chat | GPT-5-Codex | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 42.8 | 37.9 |
| Released | 2026-03-03 | 2025-09-15 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 400K |
| Max output | 16K | 128K |
| Input $ / M tokens | $1.75 | $1.25 |
| Output $ / M tokens | $14 | $10 |
| Results tracked | 18 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
GPT-5.3 Chat: 41.4 (#124), GPT-5-Codex: 42.4 (#103)
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| WeirdML | — | 54.5% |
| LMArena Coding | 1408 | — |
Agentic & Tool Use Not comparable
GPT-5.3 Chat: —, GPT-5-Codex: 31.0 (#72)
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |
Reasoning GPT-5-Codex leads
GPT-5.3 Chat: 28.5 (#102), GPT-5-Codex: 30.9 (#83)
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | — | 70.3% |
| LMArena Hard Prompts | 1399 | — |
Math Not comparable
GPT-5.3 Chat: 38.2 (#142), GPT-5-Codex: —
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| LMArena Math | 1389 | — |
Knowledge Not comparable
GPT-5.3 Chat: 38.8 (#140), GPT-5-Codex: —
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| LMArena Expert | 1397 | — |
Multilingual Not comparable
GPT-5.3 Chat: 50.3 (#124), GPT-5-Codex: —
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| LMArena Non-English | 1382 | — |
| LMArena Chinese | 1432 | — |
| LMArena French | 1397 | — |
| LMArena German | 1384 | — |
| LMArena Japanese | 1352 | — |
| LMArena Korean | 1346 | — |
| LMArena Russian | 1400 | — |
| LMArena Spanish | 1371 | — |
Instruction Following Not comparable
GPT-5.3 Chat: 72.8 (#129), GPT-5-Codex: —
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| LMArena Instruction Following | 1378 | — |
Long Context Not comparable
GPT-5.3 Chat: 42.6 (#120), GPT-5-Codex: —
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| LMArena Longer Query | 1396 | — |
Writing & Preference Not comparable
GPT-5.3 Chat: 63.1 (#68), GPT-5-Codex: —
| Benchmark | GPT-5.3 Chat | GPT-5-Codex |
|---|---|---|
| LMArena Text | 1389 | — |
| LMArena Creative Writing | 1355 | — |
| EQ-Bench Creative Writing | 1690 | — |
| LMArena Multi-Turn | 1412 | — |
Frequently asked questions
Is GPT-5.3 Chat better than GPT-5-Codex?
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 37.9 on the Noometry Index.
Which is cheaper, GPT-5.3 Chat or GPT-5-Codex?
GPT-5-Codex is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.
Is GPT-5.3 Chat or GPT-5-Codex better for coding?
They score almost the same on coding (41.4 vs 42.4); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5-Codex does, with 400K tokens against 128K.
How many benchmarks do GPT-5.3 Chat and GPT-5-Codex share?
0 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and GPT-5-Codex has 3.