AI BENCHY Compare
Inception: Mercury 2 vs StepFun: Step 3.5 Flash
Linganisha:
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-05
| Kipimo | Inception: Mercury 2 medium Toleo: 2026-02-24 | StepFun: Step 3.5 Flash medium Toleo: 2026-02-01 Inapatikana bure |
|---|---|---|
| Nafasi | #40 | #13 |
| Wastani wa alama | 48 | 74 |
| Uthabiti | 83 | 94 |
| Gharama kwa matokeo | 0.726 | 0.000 |
| Jumla ya gharama | $0.044 | $0.000 |
| Majaribio sahihi | ||
| Kiwango cha kupita kwa kila jaribio | 51.1% | 68.9% |
| Majaribio yasiyo thabiti | 3 | 1 |
| Tokeni za matokeo | 3,571 | 69,238 |
| Tokeni za hoja | 45,379 | 152,563 |
Alama dhidi ya gharama ya jumla
Mgawanyo wa kategoria
| Mbinu za kupinga AI | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 73 | 98 | 66.7% | 0 | 2,531 | 2,410 | |
| StepFun: Step 3.5 Flash | 100 | 100 | 100.0% | 0 | 13,924 | 17,208 |
| Mchanganyiko | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 100 | 100 | 100.0% | 0 | 268 | 4,887 | |
| StepFun: Step 3.5 Flash | 100 | 100 | 100.0% | 0 | 1,176 | 12,984 |
| Uchanganuzi na uchimbaji wa data | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 55 | 59 | 83.3% | 1 | 183 | 1,656 | |
| StepFun: Step 3.5 Flash | 100 | 100 | 100.0% | 0 | 600 | 13,886 |
| Mahususi kwa domeni | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 100 | 72 | 11.1% | 1 | 41 | 30,754 | |
| StepFun: Step 3.5 Flash | 40 | 72 | 44.4% | 1 | 45,350 | 90,436 |
| Ufuataji wa maagizo | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 55 | 100 | 50.0% | 0 | 14 | 958 | |
| StepFun: Step 3.5 Flash | 85 | 100 | 50.0% | 0 | 2,284 | 3,412 |
| Puzzle Solving | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 17 | 75 | 22.2% | 1 | 354 | 2,758 | |
| StepFun: Step 3.5 Flash | 40 | 100 | 33.3% | 0 | 5,629 | 10,835 |
| Mwito wa zana | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Inception: Mercury 2 | 100 | 100 | 100.0% | 0 | 180 | 1,956 | |
| StepFun: Step 3.5 Flash | 100 | 100 | 100.0% | 0 | 275 | 3,802 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Gemini 3.1 Flash Lite PreviewlowvsStep 3.5 FlashmediumInapatikana bureGPT-5.3 ChatnonevsStep 3.5 FlashmediumInapatikana bureMercury 2mediumvsQwen3.5-122B-A10BnoneMercury 2mediumvsQwen3.5-FlashnoneDeepSeek V3.2nonevsMercury 2mediumGemini 3.1 Flash Lite PreviewnonevsStep 3.5 FlashmediumInapatikana bureMercury 2mediumvsQwen3.5-27BnoneGPT-5.2 ChatnonevsStep 3.5 FlashmediumInapatikana bureMercury 2mediumvsQwen3.5-35B-A3BnoneGemini 2.5 FlashnonevsMercury 2mediumMercury 2mediumvsGPT-5.4noneGemini 3.1 Flash Lite PreviewhighvsStep 3.5 FlashmediumInapatikana bure