OpenAI
availableShows if the model has enough results for an index.GPT-5 (medium)
GPT-5 (medium) is a reasoning model from OpenAI in the GPT-5 family. 9 benchmarks count toward its score, in 5 categories.
IndexOverall score out of 100.54.7 ±8.9
CoverageShare of the index weight with results.65%
SpeedOutput tokens per second.62/s
Input / 1MUS dollars per 1M input tokens.$1.25
Output / 1MUS dollars per 1M output tokens.$10
ContextMaximum tokens in one request.400K
EloLMArena rating and rank.1406 (#136)
The index is a score out of 100. The ± range shows how much it can change.
31,428 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
9 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. |
|---|---|---|---|---|---|---|
| Artificial Analysis MATH-500 | Math | 99.1% | — | — | — | Artificial Analysis |
| τ²-Bench Tool-Agent-User Evaluation | Agentic | 86.5% | 60.9 | — | — | Victor Barres et al. |
| Artificial Analysis GPQA Diamond | Knowledge | 84.2% | 54.8 | — | — | Artificial Analysis |
| Artificial Analysis Long Context Reasoning | Reasoning | 76.0% | 60.8 | — | — | Artificial Analysis |
| Artificial Analysis MMMU-Pro | Multimodal | 74.3% | 57.9 | — | — | Artificial Analysis |
| Artificial Analysis IFBench | Instruction | 70.6% | 60.7 | — | — | Artificial Analysis |
| Artificial Analysis Omniscience Accuracy | Knowledge | 39.5% | 62.7 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 25.4% | 52.1 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 22.9% | 51.0 | — | — | Artificial Analysis |
| Critical Physics Tasks | Reasoning | 0.0% | 38.4 | — | — | Artificial Analysis |
9 benchmarks count, from 9 of 10 results. A grey row does not count. Too few models took that benchmark.