Google
availableShows if the model has enough results for an index.Gemini 1.5 Pro
Gemini 1.5 Pro is a non-reasoning model from Google. 9 benchmarks count toward its score, in 5 categories.
IndexOverall score. 50 is the middle.31.7 ±8.4
CoverageShare of the index weight with results.70%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.$1.25
Output / 1MUS dollars per 1M output tokens.$5
ContextMaximum tokens in one request.2M
EloLMArena rating and rank.N/A
50 is the middle of the board. The range shows the doubt in the index.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
9 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Artificial Analysis GPQA Diamond | Knowledge | 58.9% | 28.9 | — | — | Artificial Analysis |
| MATH level 5 | Math | 55.6% | 26.0 | — | — | Epoch AI |
| Artificial Analysis MMMU-Pro | Multimodal | 55.0% | 34.3 | — | — | Artificial Analysis |
| GPQA diamond | Knowledge | 51.5% | 25.8 | — | — | Epoch AI |
| Artificial Analysis Coding Index | Coding | 23.6% | 35.6 | — | — | Artificial Analysis |
| OTIS Mock AIME 2024-2025 | Math | 14.9% | 20.0 | — | — | Epoch AI |
| Artificial Analysis Intelligence Index | Knowledge | 7.9% | 32.3 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 4.6% | 29.6 | — | — | Artificial Analysis |
| ARC-AGI-2 (semi-private) | Reasoning | 0.8% | 40.1 | — | — | ARC Prize Foundation |
9 benchmarks count, from 9 of 9 results. A grey row does not count. Too few models took that benchmark.