Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

GPT-5.1

OpenAI

Strongest in Legal (#3 of 151), weakest in Toxicity avoidance (#159 of 272). Above par in 20 of 24 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of Kimi K2.6 and Grok 4.7.

§ 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.

Professional58.9#8/168
Legal63.8#3/151
Medical61.5#4/140
Finance54.6#50/151
Safety57.3#23/337
Safe-prompt compliance59.1#10/82
Secure code64.5#15/274
Harm refusal58.6#20/300
Fairness58.2#46/300
Factual grounding44.6#78/101
Jailbreak resistance56.6#90/272
Toxicity avoidance52.7#159/272
Knowledge55.4#45/138
Academic knowledge56.4#41/123
Reasoning53.7#50/178
Mathematics57.2#25/140
Science57.4#41/122
Reasoning49#65/140
Human preference62.4#55/342
Human preference62.4#55/342
Coding46.7#100/165
Agentic coding46.3#95/157
Agents51.1#104/268
Knowledge work51.6#69/178

§ 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-5.1, left for the other.

Jamba 1.6 Miniwon 15 · lost 0
Jamba 1.6 Largewon 15 · lost 0
Mistral Medium 3.5won 15 · lost 0
Grok 4 Fastwon 16 · lost 0
Gemini 3.5 Flash Litewon 16 · lost 0
Gemini 1.5 Flashwon 17 · lost 0
Mistral Large 3won 18 · lost 0
Gemini 1.5 Prowon 19 · lost 0
GPT OSS 20Bwon 20 · lost 0
GPT-4.1 Nanowon 22 · lost 1
Grok 4.3won 21 · lost 1
Gemini 2.0 Flashwon 20 · lost 1
Grok 3won 18 · lost 1
Kimi K2 Thinkingwon 17 · lost 1
Ling 3.0 Flashwon 17 · lost 1
Mistral Smallwon 17 · lost 1
GPT-5.4 Nanowon 17 · lost 1
Gemini 2.5 Flash Litewon 16 · lost 1
GLM-4.5won 16 · lost 1
Gemini 3.1 Flash Litewon 16 · lost 1
GPT-5.4 Miniwon 16 · lost 1
GPT OSS 120Bwon 22 · lost 2
DeepSeek V3won 22 · lost 2
GPT-4.1 Miniwon 21 · lost 2
GPT-4o Miniwon 20 · lost 2
GLM-4.6won 20 · lost 2
Command R Pluswon 16 · lost 2
Mistral Largewon 16 · lost 2
O3 Miniwon 20 · lost 3
Kimi K2won 20 · lost 3
GPT-4 Turbowon 13 · lost 2
Llama 4 Scout Instructwon 19 · lost 3
Grok 4.1 Fastwon 19 · lost 3
Command Awon 18 · lost 3
Gemma 4 31Bwon 16 · lost 3
Claude Haiku 4.5won 20 · lost 4
O4 Miniwon 19 · lost 4
DeepSeek V3.2won 19 · lost 4
Kimi K2.5won 19 · lost 4
GPT-4owon 18 · lost 4
Inkling Smallwon 13 · lost 3
Qwen3.5 Flashwon 12 · lost 3
Gemini 2.5 Flashwon 18 · lost 5
GPT-4.1won 18 · lost 5
DeepSeek R1won 18 · lost 5
Qwen3 235B A22B Instructwon 17 · lost 5
O3won 17 · lost 5
MiniMax M3won 17 · lost 5
Claude 3.5 Haikuwon 15 · lost 5
GPT-5 Miniwon 18 · lost 6
Claude Sonnet 4won 18 · lost 6
O1 Miniwon 11 · lost 4
Mimo V2.5won 11 · lost 4
Mimo V2.6 Flashwon 11 · lost 4
Claude 3.7 Sonnetwon 16 · lost 6
Grok 4won 16 · lost 6
O1won 15 · lost 6
MiniMax M2.7won 15 · lost 6
GLM-4.7won 11 · lost 5
Qwen3.6 Pluswon 11 · lost 5
GLM-5won 11 · lost 5
GPT-6 Lunawon 13 · lost 6
Claude Opus 4won 15 · lost 7
DeepSeek V4 Flashwon 15 · lost 7
GPT-5.6 Lunawon 15 · lost 7
Mimo V2.5 Prowon 14 · lost 7
Gemini 2.5 Prowon 16 · lost 8
Qwen3.8 27Bwon 10 · lost 6
Claude Sonnet 4.5won 15 · lost 9
GPT-5 Nanowon 13 · lost 8
Claude 3.5 Sonnetwon 12 · lost 8
GLM-5.3 Flashwon 13 · lost 9
Gemini 3.1 Prowon 10 · lost 8
Inklingwon 12 · lost 10
Qwen3.7 Maxwon 12 · lost 10
GLM-5.2won 12 · lost 10
Claude Opus 4.5won 9 · lost 8
Grok 4.7won 10 · lost 9
Kimi K2.6won 12 · lost 11
GPT-6 Solwon 10 · lost 10
GLM-5.1won 11 · lost 11
Gemini 3.6 Flashwon 11 · lost 11
Claude Sonnet 4.6won 10 · lost 11
Mimo V2.6 Prowon 8 · lost 9
DeepSeek V4.1 Flashwon 7 · lost 8
Grok 4.5won 10 · lost 12
Gemini 3.5 Flashwon 10 · lost 12
Qwen3.8 Maxwon 10 · lost 12
Gemini 3 Flashwon 7 · lost 9
DeepSeek V4 Prowon 10 · lost 13
GPT-5.6 Solwon 10 · lost 13
Claude Opus 4.6won 8 · lost 11
GPT-5won 10 · lost 14
Gemini 3.8 Flashwon 9 · lost 13
GPT-5.2won 8 · lost 14
GPT-5.6 Terrawon 8 · lost 14
Gemini 3 Prowon 7 · lost 13
GPT-5.5won 8 · lost 15
GPT-6 Astrawon 5 · lost 10
Muse Sparkwon 5 · lost 10
Grok 4.6won 7 · lost 15
GLM-5.3won 5 · lost 11
GPT-5.4won 7 · lost 16
Claude Opus 4.7won 6 · lost 17
Gemini 3.7 Flashwon 4 · lost 12
Kimi K3won 4 · lost 12
Muse Spark 1.1won 5 · lost 17
Muse Spark 1.2won 3 · lost 12
Claude Sonnet 5won 4 · lost 18
Claude Opus 4.8won 4 · lost 18
Claude Opus 5.5won 3 · lost 16
Claude Opus 5won 3 · lost 19
Claude Fable 5.1won 1 · lost 15
Claude Fable 5won 1 · lost 15

§ 3 · Sources

Where the numbers come from

8 publications, 29 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26
LMArena Text 1456
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 813
ARC-AGI-2 ↗1 measureread 2026-09-26
ARC-AGI-2 17.6%
SimpleBench ↗1 measureread 2026-09-26
SimpleBench 53.2%
Vals.ai ↗13 measuresread 2026-09-26
Vals · CaseLaw 73.42%Vals · LegalBench 85.68%Vals · CorpFin 63.83%Vals · TaxEval 74.86%Vals · MortgageTax 61.37%Vals · MedQA 96.38%Vals · MedCode 52.73%Vals · MedScribe 88.09%Vals · SWE-bench Verified 69.8% (Mini-SWE-agent)Vals · Vibe Code Bench 24.61% (OpenHands)Vals · GPQA Diamond 86.62%Vals · MMLU Pro 86.38%Vals · AIME 93.33%
HELM Safety ↗5 measuresread 2026-09-26
HELM Safety · HarmBench 97.6%HELM Safety · SimpleSafetyTests 99.8%HELM Safety · Anthropic Red Team 99.5%HELM Safety · BBQ 88.7%HELM Safety · XSTest 98.2%
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26
Enkrypt · Jailbreak risk 7.2%Enkrypt · Harmful content risk 16.1%Enkrypt · CBRN risk 6.5%Enkrypt · Toxicity risk 4.4%Enkrypt · Bias risk 56.3%Enkrypt · Insecure code risk 4%
Vectara · Factual consistency 87.9%

Badge

PublicAI Index badge for GPT-5.1[![PublicAI Index](https://publicai.io/model-index/badge?model=gpt-5-1)](https://publicai.io/model-index/m/gpt-5-1)