GPT-4.5 vs o3-mini
Change models
IndexAll categories, out of 100.
38.8 ±8.9
40.0 ±4.9 best
GapIndex points below the top.
−1.2 · no clear gap
Top
CoverageIndex weight that has results.
65%
85% best
SpeedOutput tokens per second.
—
173/s
EloLMArena rating and rank.
—
1320
ReleasedMonth of release.
2025-02
2025-01
Input / 1MUS dollars per 1M input tokens.
$75.00
$1.10 best
Output / 1MUS dollars per 1M output tokens.
$150.00
$4.40 best
1K chats2K tokens in, 500 out, each.
$225.00
$4.40 best
1K documents20K tokens in, 1K out, each.
$1,650.00
$26.40 best
1K agent tasks200K tokens in, 20K out, each.
$18,000.00
$308.00 best
ContextMaximum tokens in one request.
128K
200K best
AgenticMulti-step tasks with tools.
—
21.8
CodingCode writing and repair.
29.1
37.1 best
ReasoningLogic problems and puzzles.
35.6
43.2 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
48.8 best
39.0
MultilingualTasks in many languages.
31.8
—
InstructionTasks with strict prompt rules.
—
52.3
MathMath problems.
34.0
46.1 best
Benchmarks
8 sharedOnly GPT-4.5: 4Only o3-mini: 30
GPT-4.5
o3-mini