GPT-5.1 vs GPT-5

Change models
GPT-5.1OpenAI
GPT-5OpenAI
IndexAll categories, out of 100.
55.3 ±3.7 best
55.0 ±4.2
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
95% best
90%
SpeedOutput tokens per second.
50/s
76/s best
EloLMArena rating and rank.
1422 best
1406
ReleasedMonth of release.
2025-11
2025-08
Input / 1MUS dollars per 1M input tokens.
$1.25
$1.25
Output / 1MUS dollars per 1M output tokens.
$10.00
$10.00
Batch output / 1MBatch price per 1M output tokens.
$5.00
$5.00
1K chats2K tokens in, 500 out, each.
$7.50
$7.50
1K documents20K tokens in, 1K out, each.
$35.00
$35.00
1K agent tasks200K tokens in, 20K out, each.
$450.00
$450.00
ContextMaximum tokens in one request.
400K
400K
AgenticMulti-step tasks with tools.
52.4
53.1 best
CodingCode writing and repair.
53.5 best
52.5
ReasoningLogic problems and puzzles.
56.4 best
55.4
MultimodalTasks with images and text.
58.4
61.2 best
KnowledgeFacts and expert knowledge.
57.2
58.4 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
57.1
—
MathMath problems.
57.5 best
55.3

Benchmarks

29 shared
Only GPT-5.1: 15Only GPT-5: 16
GPT-5.1
GPT-5
87.6% best61 / 217
86.2%68 / 217
88.6%67 / 200
91.4% best56 / 200
85.7%20 / 149
86.0% best17 / 149
TaxEval v2Finance
74.9% best26 / 143
73.4%49 / 143
86.5% best22 / 142
85.9%25 / 142
86.6% best41 / 135
85.6%45 / 135
MMLU ProKnowledge
86.4%42 / 135
86.5% best41 / 135
CorpFin v2Finance
63.8% best39 / 131
61.1%58 / 131
24.6% best85 / 123
20.1%91 / 123
MedScribeHealthcare
88.1% best14 / 109
83.7%42 / 109
MedCodeHealthcare
52.7% best13 / 106
49.6%21 / 106
61.4%60 / 97
65.5% best41 / 97
AIMEMath
93.3%15 / 95
93.4% best14 / 95
MedQAHealthcare
96.4% best2 / 95
96.3%4 / 95
MMMU ProMultimodal
83.2% best33 / 92
81.5%39 / 92
48.0%35 / 91
50.1% best30 / 91
Chess PuzzlesReasoning
42.0% best33 / 90
36.0%42 / 90
SWE-benchCoding
69.8% best64 / 87
69.0%67 / 87
16.0%56 / 80
23.0% best39 / 80
MGSMMultilingual
93.0% best11 / 74
92.8%14 / 74