OpenAI
availableShows if the model has enough results for an index.GPT-5.4 Pro
GPT-5.4 Pro is a reasoning model from OpenAI in the GPT-5.4 family. 12 benchmarks count toward its score, in 4 categories.
IndexOverall score out of 100.76.5 ±8.7
CoverageShare of the index weight with results.60%
SpeedOutput tokens per second.1/s
Input / 1MUS dollars per 1M input tokens.$30 batch $15
Output / 1MUS dollars per 1M output tokens.$180 batch $90 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.1.05M
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change. Batch work costs less.
CapabilitiesScore per category, out of 100.
Out of 100Results
12 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| GPQA diamond | Knowledge | 94.6% | 65.6 | xhigh effort | — | Epoch AI |
| ARC-AGI-1 (semi-private) | Reasoning | 94.5% | 71.8 | xhigh effort | — | ARC Prize Foundation |
| International Physics Olympiad 2025 (Theory) | Math | 93.5% | — | — | — | Meta AI |
| BrowseComp | Agentic | 89.3% | 74.7 | — | — | OpenAI |
| ARC-AGI-2 (semi-private) | Reasoning | 83.3% | 81.8 | xhigh effort | — | ARC Prize Foundation |
| FrontierMath-Tiers-1-3-v2-Private | Math | 82.5% | 77.9 | xhigh effort | — | Epoch AI |
| Humanity's Last Exam | Knowledge | 58.7% | 78.5 | — | — | Center for AI Safety et al. |
| Chess Puzzles | Reasoning | 58.6% | 95.0 | xhigh effort | — | Epoch AI |
| FrontierMath-Tier-4-v2-Private | Math | 58.5% | 76.0 | xhigh effort | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 50.0% | 77.3 | xhigh effort | — | Epoch AI |
| SimpleQA Verified | Knowledge | 46.3% | 64.4 | xhigh effort | — | Epoch AI |
| Humanity's Last Exam without tools | Knowledge | 42.7% | 65.0 | — | — | OpenAI |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 37.5% | 84.2 | — | — | Epoch AI |
| FrontierScience | Knowledge | 36.7% | — | — | — | OpenAI |
| FrontierScience Research | Knowledge | 36.7% | — | — | — | Meta AI |
| Critical Physics Tasks | Reasoning | 30.0% | 95.0 | — | — | Artificial Analysis |
12 benchmarks count, from 13 of 16 results. A grey row does not count. Too few models took that benchmark.