AI BENCHY Compare
Google: Gemini 2.5 Flash vs StepFun: Step 3.5 Flash
Linganisha:
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | Google: Gemini 2.5 Flash medium Toleo: 2025-06-17 | StepFun: Step 3.5 Flash medium Toleo: 2026-02-01 Inapatikana bure |
|---|---|---|
| Nafasi | #16 | #17 |
| Wastani wa alama | 7.05 | 7.00 |
| Uthabiti | 9.39 | 8.32 |
| Gharama kwa matokeo | 2.762 | 0.000 |
| Jumla ya gharama | $0.249 | $0.000 |
| Majaribio sahihi | ||
| Kiwango cha kupita kwa kila jaribio | 69.1% | 73.8% |
| Majaribio yasiyo thabiti | 1 | 3 |
| Tokeni za matokeo | 975 | 60,502 |
| Tokeni za hoja | 96,701 | 117,044 |
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 |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 7.33 | 10.00 | 66.7% | 0 | 249 | 8,832 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 13,924 | 17,208 |
| Uchanganuzi na uchimbaji wa data | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 9.88 | 10.00 | 100.0% | 0 | 279 | 2,325 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 535 | 11,548 |
| Mahususi kwa domeni | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 4.00 | 7.21 | 55.6% | 1 | 18 | 80,702 | |
| StepFun: Step 3.5 Flash | 4.00 | 7.21 | 44.4% | 1 | 40,942 | 74,237 |
| Ufuataji wa maagizo | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 7.00 | 9.91 | 50.0% | 0 | 69 | 1,203 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 2,121 | 3,274 |
| Puzzle Solving | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 7.00 | 10.00 | 66.7% | 0 | 126 | 2,499 | |
| StepFun: Step 3.5 Flash | 2.00 | 4.96 | 33.3% | 2 | 2,705 | 6,975 |
| Mwito wa zana | Alama | Uthabiti | Kiwango cha kupita kwa kila jaribio | Majaribio yasiyo thabiti | Majaribio sahihi | Tokeni za matokeo | Tokeni za hoja |
|---|---|---|---|---|---|---|---|
| Google: Gemini 2.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 234 | 1,140 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 275 | 3,802 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Gemini 3 Flash PreviewnonevsStep 3.5 FlashmediumInapatikana bureGemini 2.5 FlashmediumvsGPT-5.3 ChatnoneGPT-5.3 ChatnonevsStep 3.5 FlashmediumInapatikana bureGemini 2.5 FlashmediumvsGPT-5.2 ChatnoneGPT-5.2 ChatnonevsStep 3.5 FlashmediumInapatikana bureClaude Sonnet 4.6nonevsStep 3.5 FlashmediumInapatikana bureGemini 3.1 Flash Lite PreviewnonevsStep 3.5 FlashmediumInapatikana bureClaude Sonnet 4.6nonevsGemini 2.5 FlashmediumQwen3.5 Plus 2026-02-15nonevsStep 3.5 FlashmediumInapatikana bureGemini 2.5 FlashmediumvsQwen3.5 Plus 2026-02-15noneGemini 3.1 Flash Lite PreviewhighvsStep 3.5 FlashmediumInapatikana bureGemini 3.1 Flash Lite PreviewlowvsStep 3.5 FlashmediumInapatikana bure