gpt-oss-120b (High) vs Granite 4.2 8B

Which is better for the money: gpt-oss-120b (High) by OpenAI or Granite 4.2 8B by IBM? Intelligence, total benchmark cost, and end-to-end time from Artificial Analysis & other sources, snapshot 2026-10-25.

Trade-off

OpenAIgpt-oss-120b (High)Off the frontier

Intelligence: 11.60
Total cost: $123

IBMGranite 4.2 8BOff the frontier

Intelligence: 11.10
Total cost: $53.1

Verdict

Depends on your budget

gpt-oss-120b (High) scores 0.5 points higher (11.6 vs 11.1) but costs 2.3× as much to run the benchmark ($123 vs $53.1; both mid-range class). Pick gpt-oss-120b (High) when the extra intelligence is worth the premium, otherwise Granite 4.2 8B.

Metric	gpt-oss-120b (High)	Granite 4.2 8B	Difference
Intelligence (higher is better)	11.6	11.1	−4.3% Granite 4.2 8B is 4.3% less intelligent
Total AA cost (lower is better)	$122.71	$53.07	−56.8% Granite 4.2 8B is 56.8% cheaper
End-to-end time (lower is better)	11.29s	46.99s	+316.2% Granite 4.2 8B is 316.2% slower
Price per 1M tokens (in / out)	$0.15 / $0.60	$0.06 / $0.25
Input modalities	Text	Text

Granite 4.2 8B vs gpt-oss-120b (High): 4.3% less intelligence, 56.8% less cost to run the AA benchmark, and 316.2% slower end-to-end.

Open this matchup in the interactive picker gpt-oss-120b (High): what beats it Granite 4.2 8B: what beats it

Today's Pareto frontier

Against the frontier

gpt-oss-120b (High) is off the frontier: at the same or lower cost, GPT-6 Luna (Max) scores 38.10 for $122.
Granite 4.2 8B is off the frontier: at the same or lower cost, GPT-6 Luna (High) scores 32.90 for $47.9.

gpt-oss-120b (High)Granite 4.2 8BToday's Pareto frontierOpen-weights frontierEvery other model

Matchup

Compare something else

Agents: Accept: text/markdown or ?format=md returns this page as Markdown. JSON: /api/v1/compare/gpt-oss-120b/granite-4-2-8b · Markdown: /api/v1/compare/gpt-oss-120b/granite-4-2-8b?format=md · llms.txt · agent skill