o1 vs o3-mini

Change models
o1OpenAI
o3-miniOpenAI
IndexAll categories, out of 100.
44.5 ±4.1 best
40.0 ±4.9
GapIndex points below the top.
Top
−4.5 · no clear gap
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
97/s
173/s best
EloLMArena rating and rank.
1366 best
1320
ReleasedMonth of release.
2024-12
2025-01
Input / 1MUS dollars per 1M input tokens.
$15.00
$1.10 best
Output / 1MUS dollars per 1M output tokens.
$60.00
$4.40 best
1K chats2K tokens in, 500 out, each.
$60.00
$4.40 best
1K documents20K tokens in, 1K out, each.
$360.00
$26.40 best
1K agent tasks200K tokens in, 20K out, each.
$4,200.00
$308.00 best
ContextMaximum tokens in one request.
200K
200K
AgenticMulti-step tasks with tools.
44.3 best
21.8
CodingCode writing and repair.
31.0
37.1 best
ReasoningLogic problems and puzzles.
43.6 best
43.2
MultimodalTasks with images and text.
55.9
—
KnowledgeFacts and expert knowledge.
46.8 best
39.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
51.8
52.3 best
MathMath problems.
43.9
46.1 best

Benchmarks

23 shared
Only o1: 6Only o3-mini: 15
o1
o3-mini
7.0%161 / 222
7.9% best154 / 222
76.8%99 / 217
77.0% best97 / 217
73.3%94 / 200
76.9% best92 / 200
74.7%121 / 199
74.8% best119 / 199
80.4% best86 / 149
71.5%120 / 149
62.6% best84 / 149
28.7%114 / 149
TaxEval v2Finance
74.3% best38 / 143
69.4%98 / 143
50.3%116 / 142
71.5% best84 / 142
75.7%77 / 141
77.2% best75 / 141
73.2%86 / 135
75.5% best80 / 135
MMLU ProKnowledge
83.5% best71 / 135
78.7%100 / 135
AIMEMath
71.5%53 / 95
86.5% best32 / 95
MedQAHealthcare
96.5% best1 / 95
94.8%14 / 95
41.1% best50 / 91
15.3%83 / 91
Chess PuzzlesReasoning
10.0%79 / 90
15.0% best73 / 90
14.7%83 / 90
18.6% best81 / 90
94.7%12 / 88
96.5% best8 / 88
MGSMMultilingual
89.3%47 / 74
91.3% best28 / 74
92.2%19 / 70
93.9% best10 / 70
9.3%38 / 69
12.4% best35 / 69