GPT-5.3 Instant
GPT-5.3 Instant.
13
Benchmarks with a score
0
Ranked first, out of five or more models
0
In the top three
OpenAI Mar 2026
GPT-5.3 Instant
Closed weights Flagship
No Epoch Capabilities Index score yet
- ProfBench 40.7% #63 /72
- LMCA 38.1% #64 /147
- KORA 51.5% #19 /42
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMArena (Elo) | 1,450 | #62 of 335 | Official leaderboard | |
| EQ-Bench 3 | 1,446 | #29 of 78 | Official leaderboard | |
| Creative Writing v3 | 71.0 | #48 of 120 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 62.6 | #58 of 119 | Official leaderboard | |
| BullshitBench V2 | 40% | #63 of 129 | Official leaderboard | |
| BullshitBench | 27.3% | #53 of 107 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| DTBench | 78.9% | #95 of 180 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 21 | #118 of 188 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| ProfBench | 40.7% | #63 of 72 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| KORA | 51.5% | #19 of 42 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMCA | 38.1% | #64 of 147 | Official leaderboard | |
| Conceptual Reasoning Index | 48.1 | #78 of 151 | Official leaderboard | |
| ACCoRD | 61.1 | #88 of 152 | Official leaderboard |