Claude 4 Sonnet vs o3-mini

Change models
o3-miniOpenAI
IndexAll categories, out of 100.
39.4 ±5.0
39.6 ±4.9 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
40/s
173/s best
EloLMArena rating and rank.
—
1320
ReleasedMonth of release.
2025-05
2025-01
Input / 1MUS dollars per 1M input tokens.
$3.00
$1.10 best
Output / 1MUS dollars per 1M output tokens.
$15.00
$4.40 best
1K chats2K tokens in, 500 out, each.
$13.50
$4.40 best
1K documents20K tokens in, 1K out, each.
$75.00
$26.40 best
1K agent tasks200K tokens in, 20K out, each.
$900.00
$308.00 best
ContextMaximum tokens in one request.
200K
200K
AgenticMulti-step tasks with tools.
43.8 best
23.0
CodingCode writing and repair.
51.6 best
36.9
ReasoningLogic problems and puzzles.
38.0
41.7 best
MultimodalTasks with images and text.
36.3
—
KnowledgeFacts and expert knowledge.
36.3
38.9 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
31.7
51.6 best
MathMath problems.
17.0
45.7 best

Benchmarks

8 shared
Only Claude 4 Sonnet: 9Only o3-mini: 30
Claude 4 Sonnet
o3-mini
4.3%184 / 216
7.9% best148 / 216
68.3%129 / 193
74.8% best113 / 193
52.3% best89 / 143
28.7%108 / 143
72.7% best57 / 114
49.3%97 / 114
70.8% best13 / 65
42.4%45 / 65
68.5% best4 / 46
42.4%26 / 46
57.5% best1 / 15
31.3%6 / 15
56.7% best1 / 15
32.3%5 / 15