GPT-4.1 Mini (2025-04-14)
Apr 2025
GPT-4.1 Mini (2025-04-14)Compare inon
Benchmarks of GPT-4.1 Mini (2025-04-14)35
BenchmarkByScoreRank
Knowledge15
Reasoning1
Math3
Coding12
Legacy · saturated or no longer reported4
No benchmark matches
Ranking?
Alternatives?
ModelScoreCostPer taskWhat changes
CheaperGPT-5 Nano (2025-08-07)medium+9%-80%$0.05 / $0.40Context: 1M → 400KBetterGPT-5 (2025-08-07)high+12%+391%$1.25 / $10Context: 1M → 400K
OpenR1 0528unstated+11%same$0.39 / $1.63Context: 1M → 128K+1BetterGPT-5 Mini (2025-08-07)high+12%same$0.25 / $2Context: 1M → 400KBettero3 (2025-04-16)high+12%+400%$2 / $8Context: 1M → 200KModelScoreCostPer taskWhat changes
GPT-5 Nano (2025-08-07)medium+9%-80%$0.05 / $0.40Context: 1M → 400KModelScoreCostPer taskWhat changes
GPT-5 (2025-08-07)high+12%+391%$1.25 / $10Context: 1M → 400KGPT-5 Mini (2025-08-07)high+12%same$0.25 / $2Context: 1M → 400Ko3 (2025-04-16)high+12%+400%$2 / $8Context: 1M → 200KR1 0528unstatedOpen+11%same$0.39 / $1.63Context: 1M → 128K+1GPT-5 Nano (2025-08-07)medium+9%-80%$0.05 / $0.40Context: 1M → 400KModelScoreCostPer taskWhat changes
R1 0528unstatedOpen+11%same$0.39 / $1.63Context: 1M → 128K+1DeepSeek R1 Distill Llama 70BOpen+3%+4%$0.70 / $0.80Context: 1M → 131K+1DeepSeek V3 0324unstatedOpen-13%-42%$0.24 / $0.90Context: 1M → 128K+1
Gemma 3 27BunstatedOpen-15%-86%$0.08 / $0.16Context: 1M → 131K
Llama 4 Maverick 17B 128E Instruct FP8Open-16%-50%$0.20 / $0.80ModelScoreCostPer taskWhat changes
GPT-5 (2025-08-07)medium+12%—$1.25 / $10Context: 1M → 400Ko3 (2025-04-16)high+12%—$2 / $8Context: 1M → 200KGPT-5 Mini (2025-08-07)medium+11%—$0.25 / $2Context: 1M → 400KGPT-5 Nano (2025-08-07)medium+9%—$0.05 / $0.40Context: 1M → 400KGPT-4.1 (2025-04-14)-5%—$2 / $8GPT-4ounstated-39%—$2.50 / $10Context: 1M → 128KGPT-4o Miniunstated-40%—$0.15 / $0.60Context: 1M → 128KGPT-6.1 Solmediumn/a—$0.21Remove unsupported parameters+5All OpenAI models →History
7 versionsBenchmarks
all categoriesChat & Knowledge
Arena Text · Chinese1,328.6#133
Arena Text · English1,355.8#129
Arena Text · French1,357.7#107
Arena Text · German1,350.3#98
Arena Text · instruction following1,332.5#113
Arena Text · Japanese1,289.6#89
Arena Text · Korean1,298.2#97
Arena Text · non-English1,317.9#124
Arena Text · Polish1,326#101
Arena Text · Russian1,323.9#124
Arena Text · Spanish1,319.1#122
SimpleQA Verified v112.7#74
MATH Level 587.3#7
FrontierMath4.5#32
Chess Puzzles1#68
Arena Text · overall · full cohort1,340.5#122
GPQA Diamond · Epoch65.8#86
OTIS Mock AIME 2024 202544.7#95
Coding
SWE-rebench · all · 2025-01-01 to 2025-08-0125.5#2
SWE-rebench · Go · 2025-01-01 to 2025-08-010#1
SWE-rebench · Java · 2025-01-01 to 2025-08-010#1
SWE-rebench · Rust · 2025-01-01 to 2025-08-010#1
SWE-rebench · Python · 2025-01-01 to 2025-08-0125.5#2
SWE-rebench · TypeScript · 2025-01-01 to 2025-08-010#1
SWE-rebench · all · 2025-08-01 to 2025-12-0115.8#2
SWE-rebench · Go · 2025-08-01 to 2025-12-010#1
SWE-rebench · Java · 2025-08-01 to 2025-12-010#1
SWE-rebench · Rust · 2025-08-01 to 2025-12-010#1
SWE-rebench · Python · 2025-08-01 to 2025-12-0115.8#2
SWE-rebench · TypeScript · 2025-08-01 to 2025-12-010#1
Agents & Tool Use
BFCL v450.5#13
BFCL v4 · prompt mode29.7#10
Writing & Language
Arena Text · creative writing · full cohort1,299.4#119
FAQ
How much does GPT-4.1 Mini (2025-04-14) cost?›
$0.40 per 1M input tokens and $1.60 per 1M output tokens.
Is GPT-4.1 Mini (2025-04-14) free to use?›
There is no free API; the cheapest paid price is $0.40 per 1M input tokens.
How good is GPT-4.1 Mini (2025-04-14), and what is it best at?›
#129 of 188 in Chat & Knowledge, #13 of 39 in Agents & Tool Use, #119 of 187 in Writing & Language.
Is GPT-4.1 Mini (2025-04-14) better than DeepSeek R1 Distill Llama 70B?›
On MATH Level 5, GPT-4.1 Mini (2025-04-14) scores 87.3 vs 89.9 — lower.
How can I use GPT-4.1 Mini (2025-04-14)?›
Through the OpenAI API.
What is the context window of GPT-4.1 Mini (2025-04-14)?›
1M tokens.
When was GPT-4.1 Mini (2025-04-14) released? Is there a newer version?›
Released 2025-04-14. It has been superseded by GPT-6 Luna.
Can GPT-4.1 Mini (2025-04-14) read images?›
It accepts text and images as input.
What is GPT-4.1 Mini (2025-04-14)?›
GPT-4.1 Mini (2025-04-14) is a language model from OpenAI, released Apr 2025.
What are the best alternatives to GPT-4.1 Mini (2025-04-14)?›
GPT-5 Nano (2025-08-07) (cheaper), GPT-5 (2025-08-07) (better), R1 0528 (open weights).