Urambazaji
AI BENCHY
Your ad here

AI BENCHY Compare

Modeli zilizolinganishwa

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-21

Kipimo MiniMax M2.7 MiniMax M2.7 medium Toleo: 2026-03-18 Kimi K2.5 Kimi K2.5 medium Toleo: 2026-01-27 GLM 5 GLM 5 medium Toleo: 2026-02-12 Gemini 3.1 Flash Lite Preview Gemini 3.1 Flash Lite Preview medium Toleo: 2026-03-03
Alama 5.0 7.2 8.3 8.1
Nafasi #68 #35 #11 #14
Uthabiti 5.3 7.2 8.1 10.0
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio 49.0% 72.6% 84.3% 70.6%
Majaribio yasiyo thabiti 10 6 4 0
Jumla ya uendeshaji 51 51 51 51
Gharama kwa matokeo 2.398 2.232 0.896 0.413
Jumla ya gharama $0.072 $0.201 $0.108 $0.050
Bei ya ingizo $0.300 / 1M $0.450 / 1M $0.720 / 1M $0.250 / 1M
Bei ya toleo $1.200 / 1M $2.200 / 1M $2.300 / 1M $1.500 / 1M
Tokeni za matokeo 4,517 40,907 19,833 1,737
Tokeni za hoja 47,612 75,121 38,523 26,346
Muda wa majibu (wastani) 27.32s 64.59s 17.15s 3.70s
Muda wa majibu (upeo) 117.04s 137.29s 28.96s 14.93s
Muda wa majibu (jumla) 437.10s 645.93s 154.32s 62.97s

Modeli bora kwa alama

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

Mbinu za kupinga AI Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
MiniMax M2.7 7.9 6.3 83.3% 2 40.32s 3,010 17,716
Kimi K2.5 7.3 5.8 83.3% 2 51.38s 2,789 8,880
GLM 5 10.0 10.0 100.0% 0 23.66s 480 7,056
Gemini 3.1 Flash Lite Preview 9.1 10.0 75.0% 0 2.33s 570 4,305
Mchanganyiko Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
MiniMax M2.7 4.7 1.6 66.7% 1 41.03s 369 4,480
Kimi K2.5 10.0 10.0 100.0% 0 71.37s 703 3,713
GLM 5 10.0 10.0 100.0% 0 28.96s 662 3,242
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 14.93s 327 7,347
Uchanganuzi na uchimbaji wa data Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
MiniMax M2.7 6.3 5.8 66.7% 1 21.95s 187 5,882
Kimi K2.5 10.0 10.0 100.0% 0 49.78s 563 7,940
GLM 5 7.1 5.6 83.3% 1 8.90s 567 3,734
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 2.29s 279 2,952
Mahususi kwa domeni Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
MiniMax M2.7 3.0 10.0 0.0% 0 19.00s 8 2,796
Kimi K2.5 3.5 4.4 33.3% 2 137.29s 20,753 30,564
GLM 5 3.5 4.4 33.3% 2 0ms 13,176 14,137
Gemini 3.1 Flash Lite Preview 3.0 10.0 0.0% 0 4.21s 18 5,325
Akili ya jumla Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
MiniMax M2.7 3.9 2.5 33.3% 1 38.70s 92 5,204
Kimi K2.5 6.5 3.4 66.7% 1 69.73s 3,815 4,262
GLM 5 6.1 3.1 66.7% 1 14.69s 2,020 2,248
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 3.16s 96 1,488
Ufuataji wa maagizo Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
MiniMax M2.7 3.7 1.8 50.0% 2 12.64s 213 2,457
Kimi K2.5 10.0 10.0 100.0% 0 92.47s 5,371 6,547
GLM 5 10.0 10.0 100.0% 0 7.25s 1,001 2,129
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 1.91s 72 2,121
Puzzle Solving Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
MiniMax M2.7 3.8 4.5 33.3% 2 25.62s 334 8,076
Kimi K2.5 5.3 7.3 44.4% 1 45.40s 6,671 12,403
GLM 5 10.0 10.0 100.0% 0 15.64s 1,694 4,983
Gemini 3.1 Flash Lite Preview 7.7 10.0 66.7% 0 3.58s 141 1,896
Mwito wa zana Alama Uthabiti Kiwango cha kupita kwa kila jaribio Majaribio yasiyo thabiti Majaribio sahihi Muda wa majibu (wastani) Tokeni za matokeo Tokeni za hoja
MiniMax M2.7 4.7 1.6 66.7% 1 12.05s 304 1,001
Kimi K2.5 10.0 10.0 100.0% 0 31.74s 242 812
GLM 5 10.0 10.0 100.0% 0 15.93s 233 994
Gemini 3.1 Flash Lite Preview 10.0 10.0 100.0% 0 3.80s 234 912

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

MiniMax M2.7mediumvsQwen3 Coder NextnoneMiniMax M2.7mediumvsGPT-4o-mininoneClaude Sonnet 4.6nonevsKimi K2.5mediumMercury 2nonevsMiniMax M2.7mediumMiniMax M2.7mediumvsGPT-5.4 MininoneMiniMax M2.7mediumvsNemotron 3 SupernoneInapatikana bureMiniMax M2.7mediumvsQwen3.5-9BnoneMiniMax M2.7mediumvsMistral Small 4noneGemini 3.1 Flash Lite PreviewlowvsGLM 5mediumGemini 3 Flash PreviewnonevsGLM 5mediumTrinity Large PreviewnoneInapatikana burevsMiniMax M2.7mediumGemini 3.1 Flash Lite PreviewmediumvsGPT-5.2 Chatnone