The LLM benchmark aggregator.

Claude Opus 4.8

Anthropic

Strongest in General intelligence (#5 of 178, on 1 of its 3 boards), weakest in Secure code (#122 of 270). Above par in 27 of 27 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Claude Fable 5.1 and ahead of Gemini 3.1 Pro and GPT-6 Sol.

§ 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.

Safety59.8−1.6#6/3291/3

Fairness69.2−0.8#13/2921/2

Harm refusal59.2−2.3#16/2921/2

Jailbreak resistance61.7−3.3#27/2681/1

Toxicity avoidance58−1#31/2681/1

Secure code54−12.2#122/2701/1

Professional57.6−4.8#12/1941/2

Finance58.7−3.7#9/1621/1

Medical59.8−6.7#9/1491/1

Legal56.4−9.5#31/1731/1

Core abilities59.3−6#13/1992/4

General intelligence67.6−1.8#5/1781/3

Instruction following57.1−16.7#19/621/1

Language52.1−14.5#31/621/1

Reasoning58.1−7.3#19/1954/5

Science61.4−2.1#16/1221/1

Reasoning57.4−11.6#35/1472/3

Mathematics56.7−7.1#38/1521/2

Human preference64.5−4.3#24/3541/1

Coding55.4−10.8#30/1793/6

Agentic coding55.6−11.3#32/1733/5

Agents56.8−9.6#39/2982/6

Knowledge work60.9−9.8#44/2082/2

Knowledge54.6−7.9#41/1972/3

Academic knowledge60.4−3.5#9/1231/1

Document parsing53.8−9.5#38/831/1

§ 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 Claude Opus 4.8, left for the other.

Magistral Small 1.2won 17 · lost 0

Gemini 2.5 Flash-Litewon 17 · lost 0

MiniMax M2.5won 17 · lost 0

Grok 4 Fastwon 17 · lost 0

Mistral Medium 3.5won 17 · lost 0

Gemini 1.5 Prowon 18 · lost 0

Inkling Smallwon 18 · lost 0

Qwen3.6 Pluswon 18 · lost 0

Llama 3.3 70B Instructwon 19 · lost 0

Grok 3 Miniwon 19 · lost 0

GLM-4.5won 19 · lost 0

Mistral Large 3won 19 · lost 0

Gemini 3.1 Flash-Litewon 19 · lost 0

GPT-5.4 miniwon 20 · lost 0

Gemini 3.5 Flash-Litewon 21 · lost 0

Llama 4 Scout Instructwon 22 · lost 0

Command Awon 22 · lost 0

Gemini 2.0 Flashwon 22 · lost 0

GPT-5.4 nanowon 22 · lost 0

Grok 3won 22 · lost 0

Claude Sonnet 4.6won 23 · lost 0

Llama 4 Maverick Instructwon 24 · lost 0

DeepSeek V3won 24 · lost 0

Claude Sonnet 4.5won 24 · lost 0

DeepSeek V4 Flashwon 26 · lost 0

GLM-5.2won 25 · lost 1

GPT-4.1 nanowon 23 · lost 1

GPT-4.1 miniwon 23 · lost 1

DeepSeek V3.2won 23 · lost 1

Grok 4.3won 23 · lost 1

Gemini 2.5 Prowon 23 · lost 1

Kimi K2.6won 23 · lost 1

GPT-4o miniwon 22 · lost 1

Gemini 2.5 Flashwon 22 · lost 1

Claude Haiku 4.5won 22 · lost 1

Kimi K2won 22 · lost 1

Qwen3 235B A22B Instructwon 22 · lost 1

GPT-4owon 21 · lost 1

O3 Miniwon 21 · lost 1

GPT OSS 20Bwon 20 · lost 1

Gemma 4 31Bwon 20 · lost 1

MiMo V2.5 Prowon 20 · lost 1

Kimi K2 Thinkingwon 19 · lost 1

Claude 3.7 Sonnetwon 19 · lost 1

Ling 3.0 Flashwon 17 · lost 1

GLM-4.7won 16 · lost 1

GLM-5won 16 · lost 1

NVIDIA Nemotron 3 Ultra 550B A55Bwon 24 · lost 2

GPT-6 Lunawon 23 · lost 2

GPT OSS 120Bwon 22 · lost 2

Kimi K2.5won 22 · lost 2

Grok 4won 21 · lost 2

GPT-4.1won 21 · lost 2

DeepSeek R1won 21 · lost 2

Mistral Large 4won 21 · lost 2

Claude Opus 4won 20 · lost 2

GLM-5.1won 20 · lost 2

Grok 4.1 Fastwon 19 · lost 2

MiMo V2.6 Prowon 19 · lost 2

MiMo V2.6 Flashwon 18 · lost 2

Claude Opus 4.5won 18 · lost 2

GLM-5.3 Flashwon 24 · lost 3

MiniMax M3won 23 · lost 3

Inklingwon 23 · lost 3

DeepSeek V4 Prowon 23 · lost 3

Grok 4.5won 23 · lost 3

Claude Sonnet 4won 21 · lost 3

Qwen3.7 Maxwon 21 · lost 3

O4 Miniwon 20 · lost 3

GLM-4.6won 20 · lost 3

GPT-5 nanowon 18 · lost 3

MiniMax M2.7won 18 · lost 3

O1won 17 · lost 3

GPT-5.2won 21 · lost 4

O3won 19 · lost 4

Claude Opus 4.6won 19 · lost 4

GPT-5.6 Lunawon 22 · lost 5

GPT-5.4won 22 · lost 5

Qwen3.8 27Bwon 17 · lost 4

Claude 3.5 Haikuwon 16 · lost 4

GPT-5 miniwon 20 · lost 5

GPT-5won 19 · lost 5

GPT-5.1won 17 · lost 5

Claude 3.5 Sonnetwon 14 · lost 5

Gemini 3.5 Flashwon 19 · lost 7

Gemini 3.6 Flashwon 19 · lost 7

Qwen3.8 Maxwon 18 · lost 7

Muse Spark 1.1won 17 · lost 7

Claude Haiku 5.5won 13 · lost 6

GPT-5.6 Terrawon 18 · lost 9

Grok 4.6won 17 · lost 9

Claude Sonnet 5won 17 · lost 9

DeepSeek V4.1 Flashwon 13 · lost 7

Kimi K3won 13 · lost 7

Gemini 3.8 Flashwon 17 · lost 10

GPT-5.5won 16 · lost 10

Grok 4.7won 14 · lost 9

GLM-5.3won 12 · lost 8

Gemini 3 Prowon 12 · lost 8

Claude Opus 4.7won 16 · lost 11

GPT-6 Solwon 13 · lost 11

Gemini 3.1 Prowon 11 · lost 10

Gemini 3.7 Flashwon 10 · lost 10

GPT-5.6 Solwon 12 · lost 15

Muse Spark 1.2won 7 · lost 11

Claude Sonnet 5.5won 7 · lost 12

GPT-6.1 Solwon 7 · lost 12

GPT-6 Astrawon 7 · lost 13

Claude Opus 5.5won 7 · lost 18

Claude Opus 5won 6 · lost 19

Claude Fable 5.1won 1 · lost 20

Claude Fable 5won 0 · lost 21

§ 3 · Sources

Where the numbers come from

11 publications, 40 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-11-10

LMArena Text 1482

GDPval-AA ↗1 measureread 2026-11-10

GDPval-AA 1462

AA-Briefcase ↗1 measureread 2026-11-10

AA-Briefcase 1320

Terminal-Bench ↗1 measureread 2026-11-10

Terminal-Bench 23.6% (Claude Code)

ARC-AGI-2 ↗1 measureread 2026-11-10

ARC-AGI-2 72.1%

LiveBench 1.0 ↗8 measuresread 2026-11-10

LiveBench 1.0 76.2LiveBench 1.0 · Reasoning 89.2LiveBench 1.0 · Coding 81.8LiveBench 1.0 · Agentic Coding 50.5LiveBench 1.0 · Mathematics 94.3LiveBench 1.0 · Data Analysis 66LiveBench 1.0 · Language 79.7LiveBench 1.0 · Instruction Following 72

Kagi LLM Benchmark ↗1 measureread 2026-11-10

Kagi LLM Benchmark 88.8%

SimpleBench ↗1 measureread 2026-11-10

SimpleBench 64.8%

Vals.ai ↗13 measuresread 2026-11-10

Vals · Legal Research Bench 43.75%Vals · LegalBench 83.57%Vals · Finance Agent 53.92%Vals · CorpFin 66.71%Vals · TaxEval 75.63%Vals · MortgageTax 69.91%Vals · MedCode 53.22%Vals · MedScribe 85.75%Vals · SWE-bench Verified 88.6% (Mini-SWE-agent)Vals · Vibe Code Bench 82.72% (OpenHands)Vals · Code Migration 47.25%Vals · GPQA Diamond 92.42%Vals · MMLU Pro 89.58%

ParseBench ↗6 measuresread 2026-11-10

ParseBench · Overall 62.27%ParseBench · Tables 89.65%ParseBench · Charts 49.75%ParseBench · Content faithfulness 89.02%ParseBench · Semantic formatting 71.38%ParseBench · Visual grounding 11.53%

Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-11-10

Enkrypt · Jailbreak risk 3%Enkrypt · Harmful content risk 0.6%Enkrypt · CBRN risk 8%Enkrypt · Toxicity risk 0.7%Enkrypt · Bias risk 48.1%Enkrypt · Insecure code risk 24.9%

Badge

[![PublicAI Index](https://publicai.io/model-index/badge?model=claude-opus-4-8)](https://publicai.io/model-index/m/claude-opus-4-8)