GPT-OSS 20B vs Granite 4.2 30B
Change modelsGPT-OSS 20BOpenAI
IndexAll categories, out of 100.
41.7 ±4.6 best
41.6 ±5.4
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
90% best
85%
SpeedOutput tokens per second.
310/s
—
EloLMArena rating and rank.
1288
1361 best
ReleasedMonth of release.
2025-08
2026-08
Input / 1MUS dollars per 1M input tokens.
$0.03
—
Output / 1MUS dollars per 1M output tokens.
$0.13
—
1K chats2K tokens in, 500 out, each.
$0.125
—
1K documents20K tokens in, 1K out, each.
$0.73
—
1K agent tasks200K tokens in, 20K out, each.
$8.60
—
ContextMaximum tokens in one request.
131K best
128K
AgenticMulti-step tasks with tools.
39.8
42.0 best
CodingCode writing and repair.
48.9 best
43.2
ReasoningLogic problems and puzzles.
35.3
39.2 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
36.0 best
35.0
MultilingualTasks in many languages.
37.0
—
InstructionTasks with strict prompt rules.
49.9
61.1 best
MathMath problems.
45.9
47.5 best
Benchmarks
9 sharedOnly GPT-OSS 20B: 28Only Granite 4.2 30B: 11
GPT-OSS 20B
Granite 4.2 30B