Artificial Analysis
#8of 51
Score 38.4. Best run: openai/gpt-5.5.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
OpenAI
GPT-5.5 benchmarks, ranks and price
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place GPT-5.5, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 1, 2026
#5of 85
on the LLM leaderboard, with a consensus score of 80 across 3 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Where each leaderboard places GPT-5.5
LiveBench
#2of 34
Score 79.9. Best run: GPT 5.5 xHigh.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#11of 79
Score 1482. Best run: gpt-5.5-high.
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
$11
OpenRouter: $5.00 in, $30 out. Vercel AI Gateway: $5.00 in, $30 out Context window 1.1M tokens. LiveBench cost per solved task $0.530.
Nearby
The models either side of GPT-5.5
- #2Claude Opus 583
- #3GPT-5.6 Sol83
- #4Kimi K380
- #5GPT-5.580
- #6gemini-3-pro79
- #7Claude Opus 4.879
- #8Claude Opus 4.7 xHigh Effort74
Questions about GPT-5.5
How good is GPT-5.5?
GPT-5.5 ranks #5 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 80 out of 100 across 3 leaderboards.
Is GPT-5.5 better than Kimi K3?
Not on the consensus: Kimi K3 scores 80 to GPT-5.5's 80. Compare them source by source below, since the leaderboards test different things.
Is GPT-5.5 better than gemini-3-pro?
On the consensus, yes: 80 to 79.
How much does GPT-5.5 cost?
$5.00 per million input tokens and $30 per million output tokens on OpenRouter, the cheaper listing we read. Blended at three input tokens to one output, that is $11 per million.
Is GPT-5.5 good for coding?
It scores 74.9 on the Artificial Analysis Coding Index, placing it #6 for coding among the models on this leaderboard.
These models recommend brands. See if they name yours.
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.