Artificial Analysis
Not measured by Artificial Analysis.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
OpenAI
gpt-5-nano-high benchmarks, ranks and price
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place gpt-5-nano-high, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 1, 2026
#56of 85
on the LLM leaderboard, with a consensus score of 42 across 2 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Where each leaderboard places gpt-5-nano-high
LiveBench
Not measured by LiveBench.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#64of 79
Score 1337. Best run: gpt-5-nano-high.
Blind head-to-head human votes, style controlled.
Berkeley BFCL
#17of 37
Score 51.45%. Best run: GPT-5-nano-2025-08-07 (FC).
Function calling and tool use, single turn to multi turn and web search.
Price and context
$0.14
Vercel AI Gateway: $0.050 in, $0.40 out
Nearby
The models either side of gpt-5-nano-high
- #53qwen3-30b-a3b-instruct-250743
- #54Mistral Medium 3.542
- #55Qwen3.5-122B-A10B42
- #56gpt-5-nano-high42
- #57Kimi K2.7 Code41
- #58qwen3-32b41
- #59Grok 4.341
Questions about gpt-5-nano-high
How good is gpt-5-nano-high?
gpt-5-nano-high ranks #56 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 42 out of 100 across 2 leaderboards.
Is gpt-5-nano-high better than Qwen3.5-122B-A10B?
Not on the consensus: Qwen3.5-122B-A10B scores 42 to gpt-5-nano-high's 42. Compare them source by source below, since the leaderboards test different things.
Is gpt-5-nano-high better than Kimi K2.7 Code?
On the consensus, yes: 42 to 41.
How much does gpt-5-nano-high cost?
$0.050 per million input tokens and $0.40 per million output tokens on Vercel AI Gateway, the cheaper listing we read. Blended at three input tokens to one output, that is $0.14 per million.
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.