GPT-4.1 mini vs GPT-4.1 nano

Change models
IndexAll categories, out of 100.
34.5 ±3.7 best
26.3 ±3.9
GapIndex points below the top.
Top
−8.2
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
72/s best
56/s
EloLMArena rating and rank.
1341 best
1285
ReleasedMonth of release.
2025-04
2025-04
Input / 1MUS dollars per 1M input tokens.
$0.40
$0.10 best
Output / 1MUS dollars per 1M output tokens.
$1.60
$0.40 best
Batch output / 1MBatch price per 1M output tokens.
$0.80
$0.20 best
1K chats2K tokens in, 500 out, each.
$1.60
$0.40 best
1K documents20K tokens in, 1K out, each.
$9.60
$2.40 best
1K agent tasks200K tokens in, 20K out, each.
$112.00
$28.00 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
35.3 best
24.2
CodingCode writing and repair.
28.2 best
24.8
ReasoningLogic problems and puzzles.
36.8 best
31.6
MultimodalTasks with images and text.
39.2 best
17.1
KnowledgeFacts and expert knowledge.
36.0 best
26.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
33.1 best
24.8
MathMath problems.
36.5 best
29.1

Benchmarks

35 shared
Only GPT-4.1 mini: 8
GPT-4.1 mini
GPT-4.1 nano
5.0% best176 / 222
3.8%202 / 222
44.0% best165 / 217
20.3%193 / 217
65.8% best120 / 217
48.9%149 / 217
0.0%150 / 214
0.0%150 / 214
44.7% best126 / 200
28.9%136 / 200
66.4% best141 / 199
51.2%172 / 199
20.3% best128 / 164
13.7%156 / 164
78.0% best104 / 149
61.1%141 / 149
52.9% best93 / 149
17.3%137 / 149
38.3% best111 / 146
32.0%129 / 146
TaxEval v2Finance
71.9% best70 / 143
60.8%126 / 143
58.2% best109 / 142
42.7%125 / 142
64.2% best105 / 141
50.3%124 / 141
67.9% best99 / 135
50.8%118 / 135
MMLU ProKnowledge
77.2% best105 / 135
63.5%130 / 135
0.0%101 / 133
0.0%101 / 133
0.0%120 / 131
0.0%120 / 131
CorpFin v2Finance
57.9% best86 / 131
42.1%121 / 131
3.5% best124 / 126
0.0%126 / 126
0.0%102 / 122
0.0%102 / 122