Skip to content

OpenAI

gpt-oss-120b benchmarks, ranks and price

Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place gpt-oss-120b, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.

Updated Nov 15, 2026Full leaderboardSources and method

Read Nov 15, 2026

#61of 69

on the LLM leaderboard, with a consensus score of 25 across 2 leaderboards.

Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.

By leaderboard

Where each leaderboard places gpt-oss-120b

Artificial Analysis

#12of 12

Score 3.8. Best run: openai/gpt-oss-120b.

Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.

LiveBench

Not measured by LiveBench.

Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.

LMArena

#50of 66

Score 1352. Best run: gpt-oss-120b.

Blind head-to-head human votes, style controlled.

Berkeley BFCL

Not measured by Berkeley BFCL.

Function calling and tool use, single turn to multi turn and web search.

Price and context

$0.20

OpenRouter: $0.15 in, $0.60 out. Vercel AI Gateway: $0.100 in, $0.50 out Context window 131K tokens.

Nearby

The models either side of gpt-oss-120b

  1. #58Mistral Small 431
  2. #59llama-4-scout-17b-16e-instruct30
  3. #60phi-428
  4. #61gpt-oss-120b25
  5. #62amazon-nova-pro-v1.025
  6. #63granite-3.1-8b-instruct24
  7. #64llama-3.1-nemotron-ultra-253b-v124

Questions about gpt-oss-120b

How good is gpt-oss-120b?
gpt-oss-120b ranks #61 of 69 models on the Rank.ai LLM leaderboard, with a consensus score of 25 out of 100 across 2 leaderboards.
Is gpt-oss-120b better than phi-4?
Not on the consensus: phi-4 scores 28 to gpt-oss-120b's 25. Compare them source by source below, since the leaderboards test different things.
Is gpt-oss-120b better than amazon-nova-pro-v1.0?
On the consensus, yes: 25 to 25.
How much does gpt-oss-120b cost?
$0.100 per million input tokens and $0.50 per million output tokens on Vercel AI Gateway, the cheaper listing we read. Blended at three input tokens to one output, that is $0.20 per million.
Is gpt-oss-120b good for coding?
It scores 30.4 on the Artificial Analysis Coding Index, placing it #10 for coding among the models on this leaderboard.

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

  • Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
  • Who gets namedEvery competitor in the answers, most named first.
  • The pages AI readsThe sources behind each answer.
  • Three fixesWhat to fix first, with a brief for the first article.