GPT-4o mini vs Llama 4 Scout
Change modelsGPT-4o miniOpenAI
Llama 4 ScoutMeta
IndexAll categories, out of 100.
26.2 ±4.3
26.8 ±4.8 best
GapIndex points below the top.
−0.6 · no clear gap
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
56/s
63/s best
EloLMArena rating and rank.
1286
—
ReleasedMonth of release.
2024-07
2025-04
Input / 1MUS dollars per 1M input tokens.
$0.15
$0.10 best
Output / 1MUS dollars per 1M output tokens.
$0.60
$0.30 best
1K chats2K tokens in, 500 out, each.
$0.60
$0.35 best
1K documents20K tokens in, 1K out, each.
$3.60
$2.30 best
1K agent tasks200K tokens in, 20K out, each.
$42.00
$26.00 best
ContextMaximum tokens in one request.
128K
1.31M best
AgenticMulti-step tasks with tools.
34.0 best
23.6
CodingCode writing and repair.
19.5
23.6 best
ReasoningLogic problems and puzzles.
41.1 best
32.4
MultimodalTasks with images and text.
19.0
24.0 best
KnowledgeFacts and expert knowledge.
25.7
28.0 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
18.0
25.9 best
MathMath problems.
22.0
24.2 best
Benchmarks
10 sharedOnly GPT-4o mini: 17Only Llama 4 Scout: 8
GPT-4o mini
Llama 4 Scout