GPT-4.1 nano vs GPT-4o mini

Change models
IndexAll categories, out of 100.
26.3 ±3.9 best
26.2 ±4.3
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
56/s
56/s
EloLMArena rating and rank.
1285
1286 best
ReleasedMonth of release.
2025-04
2024-07
Input / 1MUS dollars per 1M input tokens.
$0.10 best
$0.15
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$0.60
Batch output / 1MBatch price per 1M output tokens.
$0.20
—
1K chats2K tokens in, 500 out, each.
$0.40 best
$0.60
1K documents20K tokens in, 1K out, each.
$2.40 best
$3.60
1K agent tasks200K tokens in, 20K out, each.
$28.00 best
$42.00
ContextMaximum tokens in one request.
1.05M best
128K
AgenticMulti-step tasks with tools.
24.2
34.0 best
CodingCode writing and repair.
24.8 best
19.5
ReasoningLogic problems and puzzles.
31.6
41.1 best
MultimodalTasks with images and text.
17.1
19.0 best
KnowledgeFacts and expert knowledge.
26.7 best
25.7
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
24.8 best
18.0
MathMath problems.
29.1 best
22.0

Benchmarks

24 shared
Only GPT-4.1 nano: 11Only GPT-4o mini: 3
GPT-4.1 nano
GPT-4o mini
3.8%202 / 222
4.2% best194 / 222
48.9% best149 / 217
37.7%179 / 217
28.9% best136 / 200
6.9%163 / 200
51.2% best172 / 199
42.6%185 / 199
32.0% best129 / 146
31.0%134 / 146
TaxEval v2Finance
60.8% best126 / 143
60.5%127 / 143
42.7% best125 / 142
26.4%138 / 142
50.8% best118 / 135
44.2%127 / 135
MMLU ProKnowledge
63.5% best130 / 135
62.7%131 / 135
0.0%101 / 133
0.0%101 / 133
0.0%120 / 131
0.0%120 / 131
CorpFin v2Finance
42.1%121 / 131
45.5% best116 / 131
0.0%102 / 122
0.0%102 / 122
40.1%110 / 113
41.5% best109 / 113
52.8%81 / 97
54.5% best79 / 97
AIMEMath
26.5% best76 / 95
11.5%87 / 95
MedQAHealthcare
68.2%83 / 95
72.4% best81 / 95
MMMU ProMultimodal
55.1%88 / 92
56.6% best87 / 92
6.0%91 / 91
8.3% best90 / 91
Chess PuzzlesReasoning
0.0%90 / 90
3.0% best88 / 90