GPT-5 Chat
GPT-5 Chat ranks first on Spiral-Bench v1.2.
12
Benchmarks with a score
1
Ranked first, out of five or more models
1
In the top three
OpenAI Aug 2025
GPT-5 Chat
Closed weights Flagship
No Epoch Capabilities Index score yet
- BullshitBench V2 18% #91 /122
- WeirdML 39.8% #78 /112
- BullshitBench 14.6% #83 /107
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 | |
|---|---|---|---|---|
| SuperGPQA | 57.4% | #15 of 58 | Official leaderboard | |
| EQ-Bench 3 | 1,511 | #21 of 78 | Official leaderboard | |
| LMArena (Elo) | 1,426 | #94 of 333 | Official leaderboard | |
| Longform Creative Writing (EQ-Bench) | 66.8 | #49 of 119 | Official leaderboard | |
| BullshitBench V2 | 18% | #91 of 122 | Official leaderboard | |
| BullshitBench | 14.6% | #83 of 107 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WeirdML | 39.8% | #78 of 112 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SnakeBench | 26 | #60 of 183 | Official leaderboard | |
| LLM Chess | -87 | #71 of 124 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Vision Arena | 1,226 | #64 of 136 | Official leaderboard |
Safety and security
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Spiral-Bench v1.2 | 70.8 | #1 of 21 | Official leaderboard | |
| Spiral-Bench v1.0 | 58.1 | #7 of 13 | Official leaderboard |