GPT-OSS 120B vs o4-mini
Change modelsGPT-OSS 120BOpenAI
o4-miniOpenAI
IndexAll categories, out of 100.
43.4 ±4.2
44.7 ±3.0 best
GapIndex points below the top.
−1.3 · no clear gap
Top
CoverageIndex weight that has results.
90%
100% best
SpeedOutput tokens per second.
34/s
122/s best
EloLMArena rating and rank.
1365 best
1353
ReleasedMonth of release.
2025-08
2025-04
Input / 1MUS dollars per 1M input tokens.
$0.15 best
$1.10
Output / 1MUS dollars per 1M output tokens.
$0.60 best
$4.40
1K chats2K tokens in, 500 out, each.
$0.60 best
$4.40
1K documents20K tokens in, 1K out, each.
$3.60 best
$26.40
1K agent tasks200K tokens in, 20K out, each.
$42.00 best
$308.00
ContextMaximum tokens in one request.
131K
200K best
AgenticMulti-step tasks with tools.
40.1 best
38.5
CodingCode writing and repair.
42.8
45.2 best
ReasoningLogic problems and puzzles.
40.2
44.9 best
MultimodalTasks with images and text.
—
52.0
KnowledgeFacts and expert knowledge.
42.4 best
40.8
MultilingualTasks in many languages.
51.1 best
35.5
InstructionTasks with strict prompt rules.
53.5 best
53.2
MathMath problems.
51.5 best
50.5
Benchmarks
26 sharedOnly GPT-OSS 120B: 22Only o4-mini: 30
GPT-OSS 120B
o4-mini