GPT-5 mini vs Kimi K2 Thinking
Change modelsGPT-5 miniOpenAI
Kimi K2 ThinkingMoonshot AI
IndexAll categories, out of 100.
48.4 ±3.9 best
48.2 ±8.6
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
95% best
65%
SpeedOutput tokens per second.
78/s best
48/s
EloLMArena rating and rank.
1373
—
ReleasedMonth of release.
2025-08
2025-11
Input / 1MUS dollars per 1M input tokens.
$0.25 best
$0.60
Output / 1MUS dollars per 1M output tokens.
$2.00 best
$2.50
Batch output / 1MBatch price per 1M output tokens.
$1.00
—
1K chats2K tokens in, 500 out, each.
$1.50 best
$2.45
1K documents20K tokens in, 1K out, each.
$7.00 best
$14.50
1K agent tasks200K tokens in, 20K out, each.
$90.00 best
$170.00
ContextMaximum tokens in one request.
400K best
262K
AgenticMulti-step tasks with tools.
41.4
48.0 best
CodingCode writing and repair.
49.4 best
44.9
ReasoningLogic problems and puzzles.
47.0
—
MultimodalTasks with images and text.
57.9
—
KnowledgeFacts and expert knowledge.
46.1
49.2 best
MultilingualTasks in many languages.
51.8
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
52.2 best
50.5
Benchmarks
22 sharedOnly GPT-5 mini: 28
GPT-5 mini
Kimi K2 Thinking