AI BENCHY Compare

OpenAI: GPT-5.4 Nano vs StepFun: Step 3.7 Flash

Muhtasari

GPT-5.4 Nano (medium) inaongoza kwa average score: 7.5 vs 7.3. GPT-5.4 Nano (medium) ina gharama ya chini ya benchmark: $0.138 vs $0.454. GPT-5.4 Nano (medium) ni ya haraka zaidi: 13.24s vs 20.68s, na pass rates 65.2% vs 68.2%.

Muundo unaopendekezwaGPT-5.4 Nano (medium)It has the best score here (7.5), while costing about 3.3x less than Step 3.7 Flash (low).

Benchmark zimetengenezwa kutoka seti za majaribio za AI BENCHY tarehe: 2026-07-17

Kipimo	GPT-5.4 Nano GPT-5.4 Nano medium Toleo: 2026-03-17	Step 3.7 Flash Step 3.7 Flash low Toleo: 2026-05-29

Kipimo	GPT-5.4 Nano GPT-5.4 Nano medium Toleo: 2026-03-17	Step 3.7 Flash Step 3.7 Flash low Toleo: 2026-05-29
Alama	7.5	7.3
Nafasi	#51	#64
Uaminifu	10.0	10.0
Uthabiti	8.5	8.1
Majaribio sahihi
Kiwango cha kupita kwa kila jaribio	65.2%	68.2%
Majaribio yasiyo thabiti	4	5
Jumla ya uendeshaji	66	66
Gharama kwa matokeo	1.150	3.782
Jumla ya gharama	$0.138	$0.454
Bei ya ingizo	$0.200 / 1M	$0.200 / 1M
Bei ya toleo	$1.250 / 1M	$1.150 / 1M
Jumla ya tokeni za ingizo	82,819	103,833
Tokeni za matokeo	7,100	376,581
Tokeni za hoja	90,022	0
Muda wa majibu (wastani)	13.24s	20.68s
Muda wa majibu (upeo)	94.06s	124.75s
Muda wa majibu (jumla)	291.33s	455.01s

Onyesho la kizazi

Hamster playing table tennis

Prompt: Create a detailed SVG illustration of a hamster playing table tennis.

#51 GPT-5.4 Nano

medium

Gharama: $0.007
Muda: 24.6s
Tokeni: 4,943 tok

#64 Step 3.7 Flash

low

SVG batili

Gharama: $0.004
Muda: 25.3s
Tokeni: 3,072 tok

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

Kategoria:

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
GPT-5.4 Nano	8.3	10.0	75.0%	0		4.52s	606	683	2,254
Step 3.7 Flash	8.7	7.9	91.7%	1		4.02s	756	10,896	0

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
GPT-5.4 Nano	6.1	4.7	66.7%	2		19.12s	7,305	516	20,778
Step 3.7 Flash	8.2	7.2	88.9%	1		9.46s	7,437	18,685	0

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
GPT-5.4 Nano	9.9	10.0	100.0%	0		32.24s	59,730	4,435	19,221
Step 3.7 Flash	7.3	5.8	83.3%	1		66.18s	77,415	93,682	0

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
GPT-5.4 Nano	10.0	10.0	100.0%	0		2.54s	7,140	234	516
Step 3.7 Flash	7.3	5.8	83.3%	1		2.29s	7,398	2,667	0

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
GPT-5.4 Nano	5.9	7.2	55.6%	1		38.18s	619	60	43,325
Step 3.7 Flash	5.3	7.2	44.4%	1		43.31s	828	104,487	0

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
GPT-5.4 Nano	4.5	10.0	0.0%	0		4.15s	477	179	443
Step 3.7 Flash	3.4	9.3	0.0%	0		7.00s	525	4,604	0

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
GPT-5.4 Nano	9.8	10.0	100.0%	0		1.88s	660	95	521
Step 3.7 Flash	9.8	10.0	100.0%	0		1.58s	735	1,857	0

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
GPT-5.4 Nano	4.1	7.2	22.2%	1		3.79s	642	594	1,408
Step 3.7 Flash	5.5	9.9	33.3%	0		1.84s	756	3,564	0

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
GPT-5.4 Nano	10.0	10.0	100.0%	0		7.71s	5,445	234	382
Step 3.7 Flash	10.0	10.0	100.0%	0		3.25s	7,746	1,360	0

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
GPT-5.4 Nano	3.0	10.0	0.0%	0		4.81s	195	70	1,174
Step 3.7 Flash	3.0	10.0	0.0%	0		124.75s	237	134,779	0

Ulinganisho wa haraka

Badilisha jozi ya ulinganisho

Claude Opus 4.8nonevsStep 3.7 Flashlow Kimi K2.6mediumvsStep 3.7 Flashlow KAT-Coder-Pro V2.5highvsStep 3.7 Flashlow Gemini 3.1 Flash LitemediumvsStep 3.7 Flashlow Gemini 3.1 Flash Lite PreviewmediumvsStep 3.7 Flashlow Qwen3.5 Plus 2026-04-20mediumvsStep 3.7 Flashlow GPT-5.4 NanomediumvsQwen3.7 Maxnone Claude Sonnet 4.6nonevsStep 3.7 Flashlow Qwen3.7 PlusnonevsStep 3.7 Flashlow Qwen3.5-122B-A10BmediumvsStep 3.7 Flashlow Step 3.7 FlashlowvsGrok 4.3medium Step 3.7 FlashlowvsGLM 5.1medium