Request a pilot
‹ PublicAI Index

The LLM benchmark aggregator.

Muse Spark 1.1

Meta

Strongest in Finance (#3 of 151), weakest in Toxicity avoidance (#156 of 272). Above par in 24 of 29 scopes. Among the models it meets almost everywhere, it finishes behind Claude Fable 5 and Muse Spark 1.3 and ahead of Qwen3.8 Max and GPT-5.4.

§ 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.

Professional60.2#4/168
Finance61.7#3/151
Legal61.3#6/151
Medical57.9#21/140
Safety59.8#9/337
Jailbreak resistance63.5#6/272
Harm refusal60#9/300
Fairness67.8#17/300
Secure code57.1#95/274
Toxicity avoidance52.7#156/272
Human preference65.8#9/342
Human preference65.8#9/342
Knowledge57.8#20/138
Academic knowledge59.4#17/123
Coding54.9#31/165
Agentic coding56.4#31/157
Code generation49.6#49/77
Agents58.6#42/268
Computer use68.8#3/37
Knowledge work55.1#52/178
Reasoning53.5#56/178
Science60.5#23/122
Reasoning55.3#40/140
Mathematics46.9#90/140
Core abilities48.3#115/204
Instruction following53#27/57
Data analysis48.5#38/57
Language40.6#45/57
General intelligence50.8#89/204

§ 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 Muse Spark 1.1, left for the other.

Gemini 1.5 Prowon 18 · lost 0
Mistral Smallwon 19 · lost 0
Mistral Large 3won 19 · lost 0
Gemini 2.0 Flashwon 22 · lost 0
GPT-5.4 Miniwon 22 · lost 0
Gemini 3.5 Flash Litewon 22 · lost 0
Grok 4.3won 27 · lost 1
DeepSeek V3won 24 · lost 1
GPT-5.4 Nanowon 22 · lost 1
Llama 4 Scout Instructwon 21 · lost 1
Command Awon 21 · lost 1
Ling 3.0 Flashwon 17 · lost 1
GPT-4o Miniwon 22 · lost 2
GPT-4.1 Nanowon 22 · lost 2
GPT OSS 120Bwon 22 · lost 2
GPT-4.1 Miniwon 22 · lost 2
Claude Haiku 4.5won 22 · lost 2
GPT-4.1won 21 · lost 2
GLM-4.6won 21 · lost 2
Claude 3.7 Sonnetwon 20 · lost 2
GPT OSS 20Bwon 19 · lost 2
GPT-4owon 19 · lost 2
Kimi K2.6won 26 · lost 3
Grok Build 0.1won 17 · lost 2
DeepSeek V3.2won 21 · lost 3
O3 Miniwon 20 · lost 3
Kimi K2won 20 · lost 3
Mimo V2.5 Prowon 20 · lost 3
Qwen3.6 Pluswon 19 · lost 3
Grok 4.1 Fastwon 18 · lost 3
Grok 3won 17 · lost 3
Kimi K2.7 Codewon 16 · lost 3
Claude Sonnet 4.5won 21 · lost 4
Gemini 3.1 Flash Litewon 15 · lost 3
GPT-5 Miniwon 20 · lost 4
Gemini 2.5 Flashwon 20 · lost 4
GLM-5.1won 18 · lost 4
Gemma 4 31Bwon 17 · lost 4
Kimi K2 Thinkingwon 16 · lost 4
Claude 3.5 Haikuwon 16 · lost 4
O1won 16 · lost 4
Gemini 2.5 Prowon 20 · lost 5
Kimi K2.5won 20 · lost 5
MiniMax M3won 23 · lost 6
GLM-4.5won 15 · lost 4
Inklingwon 22 · lost 6
Qwen3.7 Maxwon 22 · lost 6
Grok 4won 18 · lost 5
Claude Opus 4won 18 · lost 5
GPT-5.1won 17 · lost 5
Claude Sonnet 4won 20 · lost 6
Claude 3.5 Sonnetwon 15 · lost 5
Claude Sonnet 4.6won 20 · lost 7
Qwen3 235B A22B Instructwon 17 · lost 6
O3won 18 · lost 7
GPT-5 Nanowon 15 · lost 6
MiniMax M2.7won 15 · lost 6
DeepSeek V4 Flashwon 20 · lost 8
GPT-5.6 Lunawon 20 · lost 8
GLM-5.3 Flashwon 20 · lost 8
Gemini 3.6 Flashwon 20 · lost 8
O4 Miniwon 17 · lost 7
DeepSeek R1won 17 · lost 7
GPT-5won 17 · lost 7
Qwen3.8 27Bwon 15 · lost 7
GPT-6 Lunawon 17 · lost 8
GLM-5.2won 19 · lost 9
GPT-5.2won 17 · lost 10
Claude Opus 4.5won 13 · lost 9
Mimo V2.6 Prowon 11 · lost 8
DeepSeek V4 Prowon 16 · lost 12
Gemini 3.5 Flashwon 16 · lost 12
Gemini 3 Prowon 11 · lost 9
GLM-5.3won 12 · lost 10
Grok 4.5won 15 · lost 13
GPT-5.6 Terrawon 15 · lost 13
GPT-5.4won 15 · lost 13
Qwen3.8 Maxwon 15 · lost 13
Claude Opus 4.6won 12 · lost 12
GPT-6 Solwon 12 · lost 13
Gemini 3.1 Prowon 11 · lost 12
Claude Sonnet 5won 13 · lost 15
GPT-5.5won 13 · lost 15
Gemini 3.8 Flashwon 12 · lost 16
Gemini 3.7 Flashwon 9 · lost 13
GPT-5.6 Solwon 11 · lost 17
DeepSeek V4.1 Flashwon 8 · lost 13
Grok 4.7won 9 · lost 16
Grok 4.6won 9 · lost 19
Claude Opus 4.8won 9 · lost 19
Claude Opus 4.7won 9 · lost 19
Kimi K3won 7 · lost 15
GPT-6 Astrawon 6 · lost 14
Claude Opus 5won 7 · lost 22
Claude Opus 5.5won 6 · lost 19
Muse Spark 1.2won 3 · lost 18
Claude Fable 5.1won 3 · lost 19
Muse Spark 1.3won 1 · lost 17
Claude Fable 5won 1 · lost 22

§ 3 · Sources

Where the numbers come from

7 publications, 31 figures. Every one links to the page it was read from.

LMArena Text ↗1 measureread 2026-09-26
LMArena Text 1491
GDPval-AA ↗1 measureread 2026-09-26
GDPval-AA 1208
AA-Briefcase ↗1 measureread 2026-09-26
AA-Briefcase 848
LiveBench ↗8 measuresread 2026-09-26
LiveBench 75.3LiveBench · Reasoning 87.7LiveBench · Coding 77.2LiveBench · Agentic Coding 58.5LiveBench · Mathematics 87.1LiveBench · Data Analysis 72.5LiveBench · Language 74.3LiveBench · Instruction Following 69.6
OSWorld ↗1 measureread 2026-09-26
OSWorld 80.7%
Vals.ai ↗13 measuresread 2026-09-26
Vals · Legal Research Bench 37.98%Vals · LegalBench 84.98%Vals · Harvey Legal Agent Benchmark 20%Vals · Finance Agent 57.21%Vals · CorpFin 71.29%Vals · TaxEval 79.72%Vals · MortgageTax 66.14%Vals · MedScribe 88.89%Vals · SWE-bench Verified 82% (Mini-SWE-agent)Vals · Vibe Code Bench 72.16% (OpenHands)Vals · Code Migration 31.11%Vals · GPQA Diamond 91.16%Vals · MMLU Pro 88.73%
Enkrypt AI Safety Leaderboard ↗6 measuresread 2026-09-26
Enkrypt · Jailbreak risk 1.4%Enkrypt · Harmful content risk 0%Enkrypt · CBRN risk 6.3%Enkrypt · Toxicity risk 4.4%Enkrypt · Bias risk 50.1%Enkrypt · Insecure code risk 19.1%

Badge

PublicAI Index badge for Muse Spark 1.1[![PublicAI Index](https://publicai.io/model-index/badge?model=muse-spark-1-1)](https://publicai.io/model-index/m/muse-spark-1-1)