Model comparison
GPT-5.3 Chat vs GPT-5.4 nano
GPT-5.3 Chat and GPT-5.4 nano score almost the same on the Noometry Index (42.8 vs 41.9), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. GPT-5.3 Chat scores higher in 5 categories and GPT-5.4 nano in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.3 Chat leads 63.1 to 55.7.
- GPT-5.4 nano is cheaper at $0.20 / $1.25 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Chat.
- GPT-5.4 nano accepts more context: 400K tokens versus 128K.
Side by side
| GPT-5.3 Chat | GPT-5.4 nano | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 42.8 | 41.9 |
| Released | 2026-03-03 | 2026-03-17 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 400K |
| Max output | 16K | 128K |
| Input $ / M tokens | $1.75 | $0.20 |
| Output $ / M tokens | $14 | $1.25 |
| Results tracked | 18 | 40 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 nano leads
GPT-5.3 Chat: 41.4 (#124), GPT-5.4 nano: 43.6 (#84)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Coding | 1408 | 1405 |
| SciCode | — | 46.9% |
| WeirdML | — | 49.2% |
| ALE-Bench | — | 1,005 |
Reasoning GPT-5.3 Chat leads
GPT-5.3 Chat: 28.5 (#102), GPT-5.4 nano: 23.7 (#173)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1381 |
| ARC-AGI-2 | — | 5.7% |
| Kagi LLM Benchmark | — | 39.7% |
| ARC-AGI-1 | — | 51.5% |
| CritPt | — | 9.3% |
| Chess Puzzles | — | 30% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 36.9% |
| Epoch Capabilities Index | — | 145.81 |
| ForecastBench | — | 57.3 |
Math GPT-5.4 nano leads
GPT-5.3 Chat: 38.2 (#142), GPT-5.4 nano: 40.9 (#88)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Math | 1389 | 1406 |
| FrontierMath (Tiers 1-3) | — | 44.9% |
| FrontierMath Tier 4 | — | 12.2% |
| OTIS Mock AIME 2024-2025 | — | 87.8% |
| ProofBench | — | 5% |
| FrontierMath (Feb 2025 set) | — | 25.9% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge GPT-5.4 nano leads
GPT-5.3 Chat: 38.8 (#140), GPT-5.4 nano: 41.9 (#103)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Expert | 1397 | 1396 |
| GPQA Diamond | — | 78.5% |
| SimpleQA Verified | — | 11.7% |
| Vectara Hallucination Rate | — | 3.1% |
Multimodal Not comparable
GPT-5.3 Chat: —, GPT-5.4 nano: 36.7 (#78)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Vision | — | 1196 |
Multilingual GPT-5.3 Chat leads
GPT-5.3 Chat: 50.3 (#124), GPT-5.4 nano: 48.6 (#140)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Non-English | 1382 | 1359 |
| LMArena Chinese | 1432 | 1392 |
| LMArena French | 1397 | 1396 |
| LMArena German | 1384 | 1367 |
| LMArena Japanese | 1352 | 1343 |
| LMArena Korean | 1346 | 1320 |
| LMArena Russian | 1400 | 1363 |
| LMArena Spanish | 1371 | 1371 |
Instruction Following Too close to call
GPT-5.3 Chat: 72.8 (#129), GPT-5.4 nano: 71.9 (#144)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Instruction Following | 1378 | 1362 |
Long Context Too close to call
GPT-5.3 Chat: 42.6 (#120), GPT-5.4 nano: 41.6 (#137)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Longer Query | 1396 | 1366 |
Writing & Preference GPT-5.3 Chat leads
GPT-5.3 Chat: 63.1 (#68), GPT-5.4 nano: 55.7 (#142)
| Benchmark | GPT-5.3 Chat | GPT-5.4 nano |
|---|---|---|
| LMArena Text | 1389 | 1372 |
| LMArena Creative Writing | 1355 | 1314 |
| LMArena Multi-Turn | 1412 | 1382 |
| EQ-Bench Creative Writing | 1690 | — |
Frequently asked questions
Is GPT-5.3 Chat better than GPT-5.4 nano?
GPT-5.3 Chat and GPT-5.4 nano score almost the same on the Noometry Index (42.8 vs 41.9), so choose on price, context window or the category you care about most.
Which is cheaper, GPT-5.3 Chat or GPT-5.4 nano?
GPT-5.4 nano is cheaper. It lists at $0.20 per million input tokens and $1.25 per million output tokens; GPT-5.3 Chat lists at $1.75 and $14.
Is GPT-5.3 Chat or GPT-5.4 nano better for coding?
GPT-5.4 nano scores higher on coding benchmarks: 43.6 versus 41.4 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 nano does, with 400K tokens against 128K.
How many benchmarks do GPT-5.3 Chat and GPT-5.4 nano share?
17 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and GPT-5.4 nano has 40.