GPT-5 nano vs GPT-5

Change models
GPT-5OpenAI
IndexAll categories, out of 100.
41.9 ±6.2
55.0 ±4.2 best
GapIndex points below the top.
−13.1
Top
CoverageIndex weight that has results.
75%
90% best
SpeedOutput tokens per second.
81/s best
76/s
EloLMArena rating and rank.
1320
1406 best
ReleasedMonth of release.
2025-08
2025-08
Input / 1MUS dollars per 1M input tokens.
$0.05 best
$1.25
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$10.00
Batch output / 1MBatch price per 1M output tokens.
$0.20 best
$5.00
1K chats2K tokens in, 500 out, each.
$0.30 best
$7.50
1K documents20K tokens in, 1K out, each.
$1.40 best
$35.00
1K agent tasks200K tokens in, 20K out, each.
$18.00 best
$450.00
ContextMaximum tokens in one request.
400K
400K
AgenticMulti-step tasks with tools.
—
53.1
CodingCode writing and repair.
37.2
52.5 best
ReasoningLogic problems and puzzles.
42.6
55.4 best
MultimodalTasks with images and text.
47.5
61.2 best
KnowledgeFacts and expert knowledge.
37.4
58.4 best
MultilingualTasks in many languages.
44.5
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
45.8
55.3 best

Benchmarks

32 shared
Only GPT-5 nano: 8Only GPT-5: 13
GPT-5 nano
GPT-5
69.4%114 / 217
86.2% best68 / 217
81.1%85 / 200
91.4% best56 / 200
50.1%147 / 149
86.0% best17 / 149
TaxEval v2Finance
67.4%107 / 143
73.4% best49 / 143
70.2%88 / 142
85.9% best25 / 142
63.4%105 / 135
85.6% best45 / 135
MMLU ProKnowledge
76.1%107 / 135
86.5% best41 / 135
2.6%93 / 131
9.9% best68 / 131
16.7%107 / 126
65.7% best62 / 126
0.3%99 / 122
9.6% best59 / 122
29.7%98 / 116
65.9% best62 / 116
MedScribeHealthcare
72.9%85 / 109
83.7% best42 / 109
MedCodeHealthcare
30.4%95 / 106
49.6% best21 / 106
53.6%80 / 97
65.5% best41 / 97
AIMEMath
81.2%45 / 95
93.4% best14 / 95
MedQAHealthcare
93.3%23 / 95
96.3% best4 / 95
MMMU ProMultimodal
70.9%69 / 92
81.5% best39 / 92
11.7%87 / 91
50.1% best30 / 91
Chess PuzzlesReasoning
22.0%57 / 90
36.0% best42 / 90
20.0%78 / 90
55.4% best51 / 90