‹ PublicAI Index
The LLM benchmark aggregator.
GPT-5
OpenAI
Strongest in Secure code (#10 of 268), weakest in Agents (#116 of 298). Above par in 24 of 26 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of Gemini 3.6 Flash and Gemini 3.5 Flash.
§ 1 · Profile
What it is good at
Bars run from 50 — the average of the models each source lists — so right of the line is above par. The middle column is the gap to whoever leads that scope.
Safety58.7−2.7#11/3273/3
Secure code65.1−1.1#10/2681/1
Harm refusal59.3−2.2#15/2902/2
Jailbreak resistance62.8−2.2#17/2661/1
Fairness66.2−3.8#19/2902/2
Safe-prompt compliance56.6−3.8#23/821/1
Factual grounding36.9−33.8#94/1041/1
Toxicity avoidance54.7−4.3#110/2661/1
Professional56.4−6#22/1941/2
Legal59.2−6.7#16/1731/1
Medical58.1−8.4#20/1491/1
Finance54.2−8.2#59/1621/1
Core abilities56.8−8.8#30/2001/4
General intelligence59.8−9.2#28/1801/3
Reasoning53.1−12.3#65/1953/5
Mathematics57.2−6.6#28/1521/2
Science56.6−6.9#46/1221/1
Reasoning47.9−21.1#76/1472/3
Knowledge52.8−9.7#71/1971/3
Academic knowledge56.6−7.3#40/1231/1
Coding51.7−14.4#76/1792/6
Agentic coding51.8−14.9#72/1732/5
Human preference60−8.8#87/3541/1
Human preference60−8.8#87/3541/1
Agents50.8−15.5#116/2981/6
Knowledge work51.5−19.2#87/2081/2
§ 2 · Head to head
What it beats, and what beats it
The same models turn up scope after scope. Counted once: where both were placed, who finished higher. Bars run right for GPT-5, left for the other.
§ 3 · Sources
Where the numbers come from
10 publications, 31 figures. Every one links to the page it was read from.
LMArena Text 1435
GDPval-AA 925
ARC-AGI-2 9.9%
Aider polyglot 88%
Kagi LLM Benchmark 72.7%
SimpleBench 56.7%
Vals · CaseLaw 66.45%Vals · LegalBench 86.02%Vals · CorpFin 61.07%Vals · TaxEval 73.39%Vals · MortgageTax 65.45%Vals · MedQA 96.32%Vals · MedCode 49.63%Vals · MedScribe 83.65%Vals · SWE-bench Verified 69% (Mini-SWE-agent)Vals · Vibe Code Bench 20.09% (OpenHands)Vals · GPQA Diamond 85.61%Vals · MMLU Pro 86.54%Vals · AIME 93.37%
HELM Safety · HarmBench 97.6%HELM Safety · SimpleSafetyTests 99.8%HELM Safety · Anthropic Red Team 99.1%HELM Safety · BBQ 96.8%HELM Safety · XSTest 97.1%
Enkrypt · Jailbreak risk 2.1%Enkrypt · Harmful content risk 6.7%Enkrypt · CBRN risk 7.1%Enkrypt · Toxicity risk 2.9%Enkrypt · Bias risk 40.1%Enkrypt · Insecure code risk 2.2%
Vectara · Factual consistency 84.9%
Badge
[](https://publicai.io/model-index/m/gpt-5)