GPT-4.1 nano vs o3

Change models
o3OpenAI
IndexAll categories, out of 100.
26.3 ±3.9
51.8 ±3.9 best
GapIndex points below the top.
−25.5
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
56/s
65/s best
EloLMArena rating and rank.
1285
1410 best
ReleasedMonth of release.
2025-04
2025-04
Input / 1MUS dollars per 1M input tokens.
$0.10 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$8.00
Batch output / 1MBatch price per 1M output tokens.
$0.20 best
$4.00
1K chats2K tokens in, 500 out, each.
$0.40 best
$8.00
1K documents20K tokens in, 1K out, each.
$2.40 best
$48.00
1K agent tasks200K tokens in, 20K out, each.
$28.00 best
$560.00
ContextMaximum tokens in one request.
1.05M best
200K
AgenticMulti-step tasks with tools.
24.2
51.8 best
CodingCode writing and repair.
24.8
51.0 best
ReasoningLogic problems and puzzles.
31.6
52.9 best
MultimodalTasks with images and text.
17.1
53.1 best
KnowledgeFacts and expert knowledge.
26.7
53.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
24.8
55.7 best
MathMath problems.
29.1
49.1 best

Benchmarks

30 shared
Only GPT-4.1 nano: 5Only o3: 16
GPT-4.1 nano
o3
3.8%202 / 222
20.1% best112 / 222
20.3%193 / 217
74.7% best97 / 217
48.9%149 / 217
81.8% best82 / 217
0.0%150 / 214
1.1% best118 / 214
28.9%136 / 200
83.9% best78 / 200
51.2%172 / 199
82.7% best91 / 199
61.1%141 / 149
83.8% best47 / 149
17.3%137 / 149
80.7% best67 / 149
32.0%129 / 146
71.4% best38 / 146
TaxEval v2Finance
60.8%126 / 143
74.6% best34 / 143
42.7%125 / 142
83.9% best44 / 142
50.8%118 / 135
84.1% best52 / 135
MMLU ProKnowledge
63.5%130 / 135
85.6% best55 / 135
0.0%120 / 131
6.5% best72 / 131
CorpFin v2Finance
42.1%121 / 131
59.7% best74 / 131
0.0%126 / 126
60.8% best67 / 126
0.0%102 / 122
2.9% best80 / 122
1.8%116 / 116
64.3% best63 / 116
40.1%110 / 113
70.1% best74 / 113
52.8%81 / 97
65.7% best40 / 97