AI BENCHY Compare
MoonshotAI: Kimi K2.5 vs Elephant
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-04-14
| Kipimo | Kimi K2.5 Kimi K2.5 none | Elephant Elephant medium |
|---|---|---|
| Alama | 5.5 | 5.2 |
| Nafasi | #72 | #77 |
| Uthabiti | 8.7 | 9.6 |
| Majaribio sahihi | ||
| Kiwango cha kupita kwa kila jaribio | 40.7% | 29.6% |
| Majaribio yasiyo thabiti | 3 | 1 |
| Jumla ya uendeshaji | 54 | 54 |
| Gharama kwa matokeo | 0.271 | 0.000 |
| Jumla ya gharama | $0.017 | $0.000 |
| Bei ya ingizo | $0.383 / 1M | $0.000 / 1M |
| Bei ya toleo | $1.720 / 1M | $0.000 / 1M |
| Tokeni za matokeo | 2,659 | 2,596 |
| Tokeni za hoja | 0 | 0 |
| Muda wa majibu (wastani) | 13.37s | 1.27s |
| Muda wa majibu (upeo) | 42.13s | 3.70s |
| Muda wa majibu (jumla) | 147.05s | 22.82s |
Alama dhidi ya gharama ya jumla
Muda wa majibu (wastani)
Alama vs Muda wa majibu (wastani)
Jumla ya tokeni za matokeo
Alama vs Jumla ya tokeni za matokeo
Mgawanyo wa kategoria
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
ElephantmediumvsGrok 4.20noneMistral Small 4nonevsElephantmediumgpt-oss-120bnoneInapatikana burevsElephantmediumTrinity Large PreviewnoneInapatikana burevsElephantmediumMistral Small 4mediumvsKimi K2.5noneGPT-5.4 MininonevsElephantmediumElephantmediumvsQwen3 Coder NextnoneMiniMax M2.5mediumInapatikana burevsKimi K2.5noneNemotron 3 SupernoneInapatikana burevsElephantmediumMiniMax M2.7mediumvsKimi K2.5noneElephantmediumvsGLM 5 TurbononeKimi K2.5nonevsgpt-oss-120bmediumInapatikana bure