AI BENCHY Compare
Google: Gemini 3.1 Flash Lite Preview vs StepFun: Step 3.5 Flash
Linganisha:
Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-03-03
| Kipimo | Google: Gemini 3.1 Flash Lite Preview low Toleo: 2026-03-03 | StepFun: Step 3.5 Flash medium Toleo: 2026-02-01 Inapatikana bure |
|---|---|---|
| Nafasi | #8 | #17 |
| Wastani wa alama | 7.84 | 7.00 |
| Uthabiti | 10.00 | 8.32 |
| Gharama kwa matokeo | 0.151 | 0.000 |
| Jumla ya gharama | $0.016 | $0.000 |
| Majaribio sahihi | ||
| Kiwango cha kupita kwa kila jaribio | 71.4% | 73.8% |
| Majaribio yasiyo thabiti | 0 | 3 |
| Tokeni za matokeo | 1,317 | 60,502 |
| Tokeni za hoja | 6,126 | 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 3.1 Flash Lite Preview | 7.00 | 10.00 | 66.7% | 0 | 456 | 1,224 | |
| 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 3.1 Flash Lite Preview | 9.88 | 10.00 | 100.0% | 0 | 291 | 696 | |
| 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 3.1 Flash Lite Preview | 4.00 | 10.00 | 33.3% | 0 | 18 | 1,212 | |
| 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 3.1 Flash Lite Preview | 8.50 | 10.00 | 50.0% | 0 | 72 | 753 | |
| 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 3.1 Flash Lite Preview | 10.00 | 10.00 | 100.0% | 0 | 243 | 1,248 | |
| 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 3.1 Flash Lite Preview | 10.00 | 10.00 | 100.0% | 0 | 237 | 993 | |
| StepFun: Step 3.5 Flash | 10.00 | 10.00 | 100.0% | 0 | 275 | 3,802 |
Ulinganisho wa haraka
Badilisha jozi ya ulinganisho
Gemini 3.1 Flash Lite PreviewlowvsGPT-5.3-CodexmediumGemini 3 Flash PreviewnonevsStep 3.5 FlashmediumInapatikana bureGPT-5.3 ChatnonevsStep 3.5 FlashmediumInapatikana bureClaude Sonnet 4.6mediumvsGemini 3.1 Flash Lite PreviewlowGPT-5.2 ChatnonevsStep 3.5 FlashmediumInapatikana bureGemini 3.1 Flash Lite PreviewlowvsGPT-5.2 ChatnoneGemini 3.1 Flash Lite PreviewlowvsGLM 5mediumGemini 3.1 Flash Lite PreviewlowvsGPT-5.3 ChatnoneClaude Sonnet 4.6nonevsStep 3.5 FlashmediumInapatikana bureGemini 3.1 Flash Lite PreviewnonevsStep 3.5 FlashmediumInapatikana bureGemini 3.1 Flash Lite PreviewlowvsQwen3.5-27BmediumQwen3.5 Plus 2026-02-15nonevsStep 3.5 FlashmediumInapatikana bure