Model vs model

GPT-4.1 vs GPT-4.1 mini

A debate-ready pair page: current winner, strongest alternative, decisive benchmarks, and the warning that should travel with the claim.

Use case · Everyday chatbot
Winner · GPT-4.1
Sources · All public sources

Winner

GPT-4.1

OpenAI

0benchmarks won

Chat / text
Professional reasoning

Versus · Everyday chatbot

GPT-4.1 leads this compare set for everyday chatbot.

GPT-4.10 of 0 wins

Thin verified coverage

0 shared benchmarks are still too close to call, so the win stays conditional. This compare uses all public sources, with provider-official evidence labeled separately.

Close calls: 0
Sources: All public

Full compare workspace Disagreement page

0%win share

Challenger

GPT-4.1 mini

OpenAI

0benchmarks won

Chat / text

The cases in full

GPT-4.1 case

Chat / text
Professional reasoning

GPT-4.1 mini case

Chat / text

What changes the outcome

GPT-4.1: 86 visible benchmark gaps still leave room for the result to move.
GPT-4.1 mini: 86 visible benchmark gaps still leave room for the result to move.

Why this result is surprising

The visible shared evidence is more decisive than usual for this compare set.
Very few shared benchmarks are decisively separating these models.

Why this is not a clean win

0 shared benchmarks are still too close to call, so the win stays conditional. This compare uses all public sources, with provider-official evidence labeled separately.
GPT-4.1 mini remains the strongest alternative once you change use case, mode, or missing-evidence assumptions.

Open full compare workspace Open evidence page Open disagreement page

Decisive benchmarks

28 of 114 benchmarks


Text Arena AR · rating Text · Chat / text	1,414n/a exact aliasverified runtimeContext only Row details Raw value 1,414 Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.92) Source label gpt-4.1-2025-04-14 Source row	1,383n/a exact aliasverified runtimeContext only Row details Raw value 1,383 Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.92) Source label gpt-4.1-mini-2025-04-14 Source row	n/a
Vision Arena AR · rating Vision · Vision understanding	1,214n/a exact aliasverified runtimeContext only Row details Raw value 1,214 Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.92) Source label gpt-4.1-2025-04-14 Source row	1,203n/a exact aliasverified runtimeContext only Row details Raw value 1,203 Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.92) Source label gpt-4.1-mini-2025-04-14 Source row	n/a
Intelligence Index AA · index Text · Chat / text	19n/a exact aliasverified runtimeContext only Row details Raw value 19 Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	16n/a exact aliasverified runtimeContext only Row details Raw value 16 Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
Time to first token AA · s Text · Chat / text	0.93sn/a exact aliasverified runtimeContext only Row details Raw value 0.93s Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	0.80sn/a exact aliasverified runtimeContext only Row details Raw value 0.80s Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
Output Speed AA · tokens/s Text · Chat / text	137.7 tokens/sn/a exact aliasverified runtimeContext only Row details Raw value 137.7 tokens/s Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	87.3 tokens/sn/a exact aliasverified runtimeContext only Row details Raw value 87.3 tokens/s Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
Time to first answer token AA · s Text · Chat / text	0.93sn/a exact aliasverified runtimeContext only Row details Raw value 0.93s Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	0.80sn/a exact aliasverified runtimeContext only Row details Raw value 0.80s Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
Blended price AA · /1M tokens Text · Chat / text	$3.5 /1M tokensn/a exact aliasverified runtimeContext only Row details Raw value $3.5 /1M tokens Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	$0.7 /1M tokensn/a exact aliasverified runtimeContext only Row details Raw value $0.7 /1M tokens Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
Input price AA · /1M input tokens Text · Chat / text	$2 /1M input tokensn/a exact aliasverified runtimeContext only Row details Raw value $2 /1M input tokens Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	$0.4 /1M input tokensn/a exact aliasverified runtimeContext only Row details Raw value $0.4 /1M input tokens Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
Output price AA · /1M output tokens Text · Chat / text	$8 /1M output tokensn/a exact aliasverified runtimeContext only Row details Raw value $8 /1M output tokens Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	$1.6 /1M output tokensn/a exact aliasverified runtimeContext only Row details Raw value $1.6 /1M output tokens Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
GPQA AA · % Text · Reasoning / math / science	66.6%n/a exact aliasverified runtimeContext only Row details Raw value 66.6% Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	66.4%n/a exact aliasverified runtimeContext only Row details Raw value 66.4% Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
Humanity's Last Exam AA · % Text · Reasoning / math / science	4.6%n/a exact aliasverified runtimeContext only Row details Raw value 4.6% Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	4.6%n/a exact aliasverified runtimeContext only Row details Raw value 4.6% Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a
CritPt AA · % Text · Reasoning / math / science	0%n/a exact aliasverified runtimeContext only Row details Raw value 0% Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 Source row	0%n/a exact aliasverified runtimeContext only Row details Raw value 0% Percentile n/a Last updated recent Eligibility historical_model Identity provider alias (0.94) Source label GPT-4.1 mini Source row	n/a

1-12 of 28

Page 1 of 3Page size

Text Arena

AR · rating

Text · Chat / text

1,414n/a

exact aliasverified runtimeContext only

Row details

Raw value: 1,414
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)
Source label: gpt-4.1-2025-04-14

Source row

1,383n/a

exact aliasverified runtimeContext only

Row details

Raw value: 1,383
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)
Source label: gpt-4.1-mini-2025-04-14

Source row

n/a

Vision Arena

AR · rating

Vision · Vision understanding

1,214n/a

exact aliasverified runtimeContext only

Row details

Raw value: 1,214
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)
Source label: gpt-4.1-2025-04-14

Source row

1,203n/a

exact aliasverified runtimeContext only

Row details

Raw value: 1,203
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.92)
Source label: gpt-4.1-mini-2025-04-14

Source row

n/a

Intelligence Index

AA · index

Text · Chat / text

19n/a

exact aliasverified runtimeContext only

Row details

Raw value: 19
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

16n/a

exact aliasverified runtimeContext only

Row details

Raw value: 16
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

Time to first token

AA · s

Text · Chat / text

0.93sn/a

exact aliasverified runtimeContext only

Row details

Raw value: 0.93s
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

0.80sn/a

exact aliasverified runtimeContext only

Row details

Raw value: 0.80s
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

Output Speed

AA · tokens/s

Text · Chat / text

137.7 tokens/sn/a

exact aliasverified runtimeContext only

Row details

Raw value: 137.7 tokens/s
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

87.3 tokens/sn/a

exact aliasverified runtimeContext only

Row details

Raw value: 87.3 tokens/s
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

Time to first answer token

AA · s

Text · Chat / text

0.93sn/a

exact aliasverified runtimeContext only

Row details

Raw value: 0.93s
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

0.80sn/a

exact aliasverified runtimeContext only

Row details

Raw value: 0.80s
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

Blended price

AA · /1M tokens

Text · Chat / text

$3.5 /1M tokensn/a

exact aliasverified runtimeContext only

Row details

Raw value: $3.5 /1M tokens
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

$0.7 /1M tokensn/a

exact aliasverified runtimeContext only

Row details

Raw value: $0.7 /1M tokens
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

Input price

AA · /1M input tokens

Text · Chat / text

$2 /1M input tokensn/a

exact aliasverified runtimeContext only

Row details

Raw value: $2 /1M input tokens
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

$0.4 /1M input tokensn/a

exact aliasverified runtimeContext only

Row details

Raw value: $0.4 /1M input tokens
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

Output price

AA · /1M output tokens

Text · Chat / text

$8 /1M output tokensn/a

exact aliasverified runtimeContext only

Row details

Raw value: $8 /1M output tokens
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

$1.6 /1M output tokensn/a

exact aliasverified runtimeContext only

Row details

Raw value: $1.6 /1M output tokens
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

GPQA

AA · %

Text · Reasoning / math / science

66.6%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 66.6%
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

66.4%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 66.4%
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

Humanity's Last Exam

AA · %

Text · Reasoning / math / science

4.6%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 4.6%
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

4.6%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 4.6%
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

CritPt

AA · %

Text · Reasoning / math / science

0%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 0%
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1

Source row

0%n/a

exact aliasverified runtimeContext only

Row details

Raw value: 0%
Percentile: n/a
Last updated: recent
Eligibility: historical_model
Identity: provider alias (0.94)
Source label: GPT-4.1 mini

Source row

n/a

GPT-4.1 vs GPT-4.1 mini

GPT-4.1

GPT-4.1 leads this compare set for everyday chatbot.

GPT-4.1 mini

GPT-4.1 case

GPT-4.1 mini case

What changes the outcome

Why this result is surprising

Why this is not a clean win

Share the recommendation with the source data attached.

Open or copy the stable surfaces

Use the exact public framing

Pick the voice before you post

Compose a post that keeps the warning attached

Decisive benchmarks

Loading model comparison.

GPT-4.1 vs GPT-4.1 mini

GPT-4.1

GPT-4.1 leads this compare set for everyday chatbot.

GPT-4.1 mini

GPT-4.1 case

GPT-4.1 mini case

What changes the outcome

Why this result is surprising

Why this is not a clean win

Share the recommendation with the source data attached.

Open or copy the stable surfaces

Use the exact public framing

Pick the voice before you post

Compose a post that keeps the warning attached

Decisive benchmarks