Google
availableShows if the model has enough results for an index.Gemini 2.5 Flash (Preview)
Gemini 2.5 Flash (Preview) is a model from Google. 8 benchmarks count toward its score, in 6 categories.
IndexOverall score out of 100.46.5 ±6.7
CoverageShare of the index weight with results.90%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.N/A
Output / 1MUS dollars per 1M output tokens.N/A
ContextMaximum tokens in one request.N/A
EloLMArena rating and rank.N/A
The index is a score out of 100. The ± range shows how much it can change.
CapabilitiesScore per category, out of 100.
Out of 100Results
8 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. |
|---|---|---|---|---|---|---|
| MGSM | Multilingual | 89.9% | — | — | 9 Jan 2026 | Vals AI |
| MGSM | Multilingual | 89.9% | — | — | 9 Jan 2026 | Vals AI |
| MMLU Pro | Knowledge | 83.7% | 52.4 | — | 1 Sept 2026 | Vals AI |
| MMLU Pro | Knowledge | 83.7% | 52.4 | — | 1 Sept 2026 | Vals AI |
| GPQA Diamond | Knowledge | 81.6% | 53.5 | — | 1 Sept 2026 | Vals AI |
| GPQA Diamond | Knowledge | 81.6% | 53.5 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 79.5% | 56.7 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 79.5% | 56.7 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 75.1% | 52.6 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 75.1% | 52.6 | — | 1 Sept 2026 | Vals AI |
| AIME | Math | 49.8% | 36.9 | — | 16 Apr 2026 | Vals AI |
| AIME | Math | 49.8% | 36.9 | — | 16 Apr 2026 | Vals AI |
| ARC-AGI-1 (semi-private) | Reasoning | 33.3% | 43.0 | — | — | ARC Prize Foundation |
| Terminal-Bench 1.0 | Agentic | 31.3% | 38.0 | — | 12 Jan 2026 | Vals AI |
| Terminal-Bench 1.0 | Agentic | 31.3% | 38.0 | — | 12 Jan 2026 | Vals AI |
| ARC-AGI-2 (semi-private) | Reasoning | 1.7% | 40.6 | — | — | ARC Prize Foundation |
8 benchmarks count, from 14 of 16 results. A grey row does not count. Too few models took that benchmark.