GPT-OSS 20B vs LFM3-1.7B
Change modelsGPT-OSS 20BOpenAI
LFM3-1.7BLiquidAI
IndexAll categories, out of 100.
41.7 ±4.6 best
41.5 ±6.5
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
90% best
75%
SpeedOutput tokens per second.
310/s best
218/s
EloLMArena rating and rank.
1288
—
ReleasedMonth of release.
2025-08
2026-10
Input / 1MUS dollars per 1M input tokens.
$0.03 best
$0.08
Output / 1MUS dollars per 1M output tokens.
$0.13 best
$0.20
1K chats2K tokens in, 500 out, each.
$0.125 best
$0.26
1K documents20K tokens in, 1K out, each.
$0.73 best
$1.80
1K agent tasks200K tokens in, 20K out, each.
$8.60 best
$20.00
ContextMaximum tokens in one request.
131K
262K best
AgenticMulti-step tasks with tools.
39.8
46.4 best
CodingCode writing and repair.
48.9 best
37.0
ReasoningLogic problems and puzzles.
35.3
43.5 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
36.0 best
28.8
MultilingualTasks in many languages.
37.0
—
InstructionTasks with strict prompt rules.
49.9
57.6 best
MathMath problems.
45.9
—
Benchmarks
4 sharedOnly GPT-OSS 20B: 33Only LFM3-1.7B: 21
GPT-OSS 20B
LFM3-1.7B