- Nafasi
- #65
- Jumla ya tokeni za matokeo
- 444,665
- Muda wa majibu (wastani)
- 32.88s
- Jumla ya gharama
- $0.591
DeepSeek V4.1 Flash (medium) vs Kimi K3.1 Pro (low)
Kimi K3.1 Pro (low) inaongoza kwa average score: 8.8 vs 8.7. DeepSeek V4.1 Flash (medium) ina gharama ya chini ya benchmark: $0.591 vs $1.836. DeepSeek V4.1 Flash (medium) ni ya haraka zaidi: 32.88s vs 47.50s, na pass rates 73.9% vs 81.2%.
Modeli zilizolinganishwa
- Nafasi
- #60
- Jumla ya tokeni za matokeo
- 139,158
- Muda wa majibu (wastani)
- 47.50s
- Jumla ya gharama
- $1.836
Muundo unaopendekezwa
DeepSeek V4.1 Flash (medium)
Its score stays close to the best score here (8.7 vs 8.8), while costing about 3.1x less than Kimi K3.1 Pro (low).
Ulinganisho wa kina
| Kipimo | DeepSeek V4.1 Flash DeepSeek V4.1 Flash medium | Kimi K3.1 Pro Kimi K3.1 Pro low |
|---|---|---|
| Alama | 8.7 | 8.8 |
| Nafasi | #65 | #60 |
| Uaminifu | 9.6 | 8.4 |
| Uthabiti | 9.3 | 8.9 |
| Majaribio | 69/69 | 69/69 |
| Majaribio sahihi | ||
| Kiwango cha kupita kwa kila jaribio | 73.9% | 81.2% |
| Majaribio yasiyo thabiti | 2 | 3 |
| Jumla ya uendeshaji | 69 | 69 |
| Gharama kwa matokeo | 1.757 | 10.796 |
| Jumla ya gharama | $0.591 | $1.836 |
| Bei ya ingizo | $0.013 / 1M | $2.000 / 1M |
| Bei ya toleo | $1.320 / 1M | $10.000 / 1M |
| Bei ya kusoma akiba | $0.013 / 1M | $0.200 / 1M |
| Bei ya kuandika akiba | Haipo | Haipo |
| Jumla ya tokeni za ingizo | 280,643 | 221,802 |
| Tokeni za matokeo | 7,342 | 12,498 |
| Tokeni za hoja | 437,323 | 126,660 |
| Muda wa majibu (wastani) | 32.88s | 47.50s |
| Muda wa majibu (upeo) | 276.31s | 506.95s |
| Muda wa majibu (jumla) | 756.34s | 1092.61s |
| Vigezo | 748B jumla (16B vinavyotumika) | ~2.8T jumla (~104B vinavyotumika) |
| Upatikanaji | Chanzo huria | Imefungwa |
Bei za akiba zinahusu tokeni za ingizo. Kusoma hutumia tena maelekezo yaliyohifadhiwa; kuandika huyahifadhi na kunaweza kuongeza gharama. Tokeni za matokeo hutumia bei ya matokeo.
Onyesho la kizazi cha modeli
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#65 DeepSeek V4.1 Flash
medium- Gharama
- $0.014
- Muda
- 34.7s
- Tokeni
- 11,541 tok
#60 MoonshotAI: Kimi K3.1 Pro
low
fetch failed
- Gharama
- $0.000
- Muda
- 10.7s
- Tokeni
- 0 tok
Mgawanyo wa kategoria
| Kazi za mawakala | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 47.59s | 192,135 | 1,932 | 11,917 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 69.28s | 103,362 | 1,789 | 2,468 |
| Mbinu za kupinga AI | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 8.3 | 10.0 | 75.0% | 0 | 3.07s | 852 | 156 | 4,108 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 5.90s | 1,650 | 286 | 1,982 |
| Uandishi wa msimbo | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 34.45s | 7,509 | 396 | 71,345 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 18.91s | 8,070 | 468 | 7,531 |
| Mchanganyiko | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 22.21s | 66,161 | 3,956 | 24,673 | |
| Kimi K3.1 Pro | 6.5 | 10.0 | 50.0% | 0 | 52.27s | 88,134 | 8,439 | 5,435 |
| Uchanganuzi na uchimbaji wa data | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 6.5 | 10.0 | 50.0% | 0 | 3.77s | 2,397 | 120 | 998 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 5.31s | 7,845 | 273 | 394 |
| Mahususi kwa domeni | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 2.9 | 7.2 | 11.1% | 1 | 153.01s | 909 | 24 | 298,454 | |
| Kimi K3.1 Pro | 4.1 | 4.4 | 44.5% | 2 | 243.49s | 1,515 | 150 | 99,091 |
| Akili ya jumla | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 3.13s | 549 | 131 | 581 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 7.96s | 735 | 166 | 608 |
| Ufuataji wa maagizo | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 9.69s | 783 | 63 | 1,483 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 5.84s | 1,185 | 147 | 961 |
| Utatuzi wa mafumbo | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 8.7 | 7.7 | 88.9% | 1 | 8.01s | 828 | 293 | 12,340 | |
| Kimi K3.1 Pro | 7.6 | 7.2 | 77.8% | 1 | 7.29s | 1,425 | 376 | 1,588 |
| Mwito wa zana | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 10.0 | 10.0 | 100.0% | 0 | 15.33s | 8,259 | 258 | 296 | |
| Kimi K3.1 Pro | 10.0 | 10.0 | 100.0% | 0 | 11.24s | 7,413 | 348 | 227 |
| Maarifa ya jumla | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Muda wa majibu (wastani) | Tokeni za ingizo | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash | 3.0 | 10.0 | 0.0% | 0 | 20.25s | 261 | 13 | 11,128 | |
| Kimi K3.1 Pro | 3.0 | 10.0 | 0.0% | 0 | 44.64s | 468 | 56 | 6,375 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
DeepSeek V4.1 FlashmediumvsKimi K3.1 PromaxDeepSeek V4.1 FlashmediumvsMuse Spark 1.2lowKimi K3.1 ProlowvsGPT-5.4mediumKimi K3.1 ProlowvsPareto 26.9defaultClaude Fable 5mediumvsKimi K3.1 ProlowMuse Spark 1.1mediumvsKimi K3.1 ProlowMuse Spark 1.2mediumvsKimi K3.1 ProlowDeepSeek V4.1 FlashmediumvsQwen3.8 27BhighInapatikana bureMuse Spark OpenmediumvsKimi K3.1 ProlowDeepSeek V4.1 FlashhighvsKimi K3.1 ProlowDeepSeek V4.1 FlashmediumvsQwen3.8 MAXlowDeepSeek V4.1 FlashmediumvsGPT-6 Sollow