Zyphra
partialShows if the model has enough results for an index.ZAYA1-VL-8B
ZAYA1-VL-8B is a non-reasoning model from Zyphra in the ZAYA1 family. 2 benchmarks count toward its score, in 1 category.
IndexOverall score out of 100.Unranked
CoverageShare of the index weight with results.10%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.Free
Output / 1MUS dollars per 1M output tokens.Free
ContextMaximum tokens in one request.131K
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
2 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. |
|---|---|---|---|---|---|---|
| CountBench | Multimodal | 88.1% | — | — | — | Qwen |
| AI2D test split | Multimodal | 87.5% | — | — | — | Qwen |
| RefCOCO average | Multimodal | 84.3% | — | — | — | RefCOCO dataset authors |
| RealWorldQA | Multimodal | 65.0% | 16.9 | — | — | Qwen |
| Massive Multi-discipline Multimodal Understanding | Multimodal | 46.0% | 16.2 | — | — | MMMU authors |
2 benchmarks count, from 2 of 5 results. A grey row does not count. Too few models took that benchmark.