GPT-5 Nano (2025-08-07)
Aug 2025
GPT-5 Nano (2025-08-07)Compare inon
Benchmarks of GPT-5 Nano (2025-08-07)14
BenchmarkByScoreRank
Knowledge2
Reasoning1
Math5
Writing2
Legacy · saturated or no longer reported4
No benchmark matches
Rankingat high effort?
Alternatives?
ModelScoreCostPer taskWhat changes
BetterClaude Opus 4.5unstated+51%+7,173%$5 / $25Context: 400K → 200K
OpenKimi K2 0711unstated+15%+536%$0.50 / $2Context: 400K → 128K+2BetterClaude Sonnet 4.5unstated+42%+4,264%$3 / $15BetterClaude Haiku 4.5unstated+34%+1,355%$1 / $5Context: 400K → 200KBettero3 (2025-04-16)unstated+23%+2,445%$2 / $8Context: 400K → 200KModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
Claude Opus 4.5unstated+51%+7,173%$5 / $25Context: 400K → 200KClaude Sonnet 4.5unstated+42%+4,264%$3 / $15Claude Haiku 4.5unstated+34%+1,355%$1 / $5Context: 400K → 200Ko3 (2025-04-16)unstated+23%+2,445%$2 / $8Context: 400K → 200KKimi K2 0711unstatedOpen+15%+536%$0.50 / $2Context: 400K → 128K+2ModelScoreCostPer taskWhat changes
Kimi K2 0711unstatedOpen+15%+536%$0.50 / $2Context: 400K → 128K+2
Qwen3 235B A22B Instruct 2507unstatedOpensame+49%$0.09 / $0.55Context: 400K → 262K+1NNanbeige4 3B Thinking 2511Opensame——Context: 400K → 66K+1Qwen3 32BunstatedOpen-5%+791%$0.70 / $2.80Context: 400K → 33K+1
Command AunstatedOpen-10%+3,082%$2.50 / $10Context: 400K → 256K+1ModelScoreCostPer taskWhat changes
o3 (2025-04-16)unstated+23%—$2 / $8Context: 400K → 200KGPT-5.2 (2025-12-11)unstated+9%—$1.75 / $14GPT-5 Mini (2025-08-07)unstated+8%—$0.25 / $2GPT-4.1 (2025-04-14)+5%—$2 / $8GPT-4.1 Mini (2025-04-14)-2%—$0.40 / $1.60GPT-6.1 Solmediumn/a—$0.21Remove unsupported parameters+5GPT-6 Lunamediumn/a—$0.017Function calling only with none · Chat Completions+3GPT-6 Solmediumn/a—$0.25All OpenAI models →Benchmarks
all categoriesChat & Knowledge
SimpleQA Verified v111.7#75
MATH Level 594.9#5
FrontierMath8.3#28
FrontierMath Tier 4 (v2)2.4#52
Chess Puzzles22#47
GPQA Diamond · Epoch69.4#82
OTIS Mock AIME 2024 202581.1#70
FAQ
How much does GPT-5 Nano (2025-08-07) cost?›
$0.05 per 1M input tokens and $0.40 per 1M output tokens.
Is GPT-5 Nano (2025-08-07) free to use?›
There is no free API; the cheapest paid price is $0.05 per 1M input tokens.
How good is GPT-5 Nano (2025-08-07), and what is it best at?›
#75 of 83 in Chat & Knowledge, #11 of 39 in Agents & Tool Use, #92 of 95 in Writing & Language.
Is GPT-5 Nano (2025-08-07) better than Qwen3 235B A22B Instruct 2507?›
On BFCL v4, GPT-5 Nano (2025-08-07) scores 51.5 vs 52.2 — about the same.
How can I use GPT-5 Nano (2025-08-07)?›
Through the OpenAI API.
What is the context window of GPT-5 Nano (2025-08-07)?›
400K tokens.
When was GPT-5 Nano (2025-08-07) released? Is there a newer version?›
Released 2025-08-07. It has been superseded by GPT-5.6 Luna.
Can GPT-5 Nano (2025-08-07) read images?›
It accepts text and images as input.
What is GPT-5 Nano (2025-08-07)?›
GPT-5 Nano (2025-08-07) is a language model from OpenAI, released Aug 2025.
What are the best alternatives to GPT-5 Nano (2025-08-07)?›
Claude Opus 4.5 (better), Kimi K2 0711 (open weights).