Rankings / Meta AI
Muse Spark
released 2026-04-08
BenchAtlas Index
as of 2026-07-14
base configuration
rank #60
11 families · 5 categories · high
base configuration
rank #97
8 families · 4 categories · medium
Benchmark evidence
48 results
agentic coding
| τ²-Bench | 91.5 % | independent | Artificial Analysis | |
| τ²-Bench subset=banking | 19.6 % | independent | Artificial Analysis |
coding
| SciCode | 51.5 % | independent | Artificial Analysis |
external indices
| AA Coding Index | 58.6 points | independent | Artificial Analysis | |
| Intelligence Index v4.1 | 43.1 points | independent | Artificial Analysis | |
| ECI | 154.3 points | independent | Epoch AI Benchmarking Hub |
factuality
| SimpleQA Verified | 66.3 % | independent | Epoch AI Benchmarking Hub 2026-04-08 |
human preference
| Coding (style control)older version arena=text · category=coding · style_control=true | 1525.2 1515.1–1535.4 | community | LMArena Leaderboard Dataset | |
| Chinese (style control)older version arena=text · category=chinese · style_control=true | 1523.3 1501.7–1544.9 | community | LMArena Leaderboard Dataset | |
| Industry Software And It Services (style control)older version arena=text · category=industry_software_and_it_services · style_control=true | 1518.9 1510.3–1527.5 | community | LMArena Leaderboard Dataset | |
| Industry Medicine And Healthcare (style control)older version arena=text · category=industry_medicine_and_healthcare · style_control=true | 1506.9 1487.1–1526.8 | community | LMArena Leaderboard Dataset | |
| Hard Prompts English (style control)older version arena=text · category=hard_prompts_english · style_control=true | 1506.1 1496.6–1515.6 | community | LMArena Leaderboard Dataset | |
| Industry Legal And Government (style control)older version arena=text · category=industry_legal_and_government · style_control=true | 1504.8 1484.9–1524.7 | community | LMArena Leaderboard Dataset | |
| Hard Prompts (style control)older version arena=text · category=hard_prompts · style_control=true | 1504.3 1497.3–1511.4 | community | LMArena Leaderboard Dataset | |
| Exclude Ties (style control)older version arena=text · category=exclude_ties · style_control=true | 1500.0 1492.4–1507.7 | community | LMArena Leaderboard Dataset | |
| Industry Life And Physical And Social Science (style control)older version arena=text · category=industry_life_and_physical_and_social_science · style_control=true | 1498.1 1485.2–1511.0 | community | LMArena Leaderboard Dataset | |
| English (style control)older version arena=text · category=english · style_control=true | 1494.9 1487.1–1502.7 | community | LMArena Leaderboard Dataset | |
| Multi Turn (style control)older version arena=text · category=multi_turn · style_control=true | 1492.3 1478.7–1505.8 | community | LMArena Leaderboard Dataset | |
| Industry Business And Management And Financial Operations (style control)older version arena=text · category=industry_business_and_management_and_financial_operations · style_control=true | 1488.6 1476.7–1500.5 | community | LMArena Leaderboard Dataset | |
| Overall (style control) arena=text · category=overall · style_control=true | 1487.6 1481.7–1493.5 | community | LMArena Leaderboard Dataset | |
| Expert (style control)older version arena=text · category=expert · style_control=true | 1486.4 1469.4–1503.3 | community | LMArena Leaderboard Dataset | |
| Russian (style control)older version arena=text · category=russian · style_control=true | 1481.5 1465.6–1497.4 | community | LMArena Leaderboard Dataset | |
| Non English (style control)older version arena=text · category=non_english · style_control=true | 1477.0 1469.4–1484.6 | community | LMArena Leaderboard Dataset | |
| Longer Query (style control)older version arena=text · category=longer_query · style_control=true | 1473.5 1464.5–1482.4 | community | LMArena Leaderboard Dataset | |
| Industry Mathematical (style control)older version arena=text · category=industry_mathematical · style_control=true | 1469.5 1448.5–1490.4 | community | LMArena Leaderboard Dataset | |
| Math (style control)older version arena=text · category=math · style_control=true | 1463.1 1443.2–1483.1 | community | LMArena Leaderboard Dataset | |
| Instruction Following (style control)older version arena=text · category=instruction_following · style_control=true | 1463.0 1453.7–1472.3 | community | LMArena Leaderboard Dataset | |
| Creative Writing (style control)older version arena=text · category=creative_writing · style_control=true | 1462.4 1448.3–1476.5 | community | LMArena Leaderboard Dataset | |
| Industry Entertainment And Sports And Media (style control)older version arena=text · category=industry_entertainment_and_sports_and_media · style_control=true | 1460.5 1448.2–1472.9 | community | LMArena Leaderboard Dataset | |
| Industry Writing And Literature And Language (style control)older version arena=text · category=industry_writing_and_literature_and_language · style_control=true | 1458.1 1447.0–1469.1 | community | LMArena Leaderboard Dataset |
knowledge science
| GPQA Diamond | 89.8 % | independent | Epoch AI Benchmarking Hub 2026-04-08 | |
| GPQA Diamond implementation=vals-ai | 89.6 % | independent | Vals AI | |
| GPQA Diamond implementation=artificial-analysis | 88.4 % | independent | Artificial Analysis | |
| Humanity's Last Exam contamination=Potential contamination warning: This model was evaluated after the public release of HLE, allowing model builder access to the prompts and solutions. · implementation=scale | 40.6 % 38.6–42.5 | independent | Scale Labs | |
| Humanity's Last Exam implementation=artificial-analysis | 39.9 % | independent | Artificial Analysis | |
| MMLU-Pro implementation=vals-ai | 87.3 % | independent | Vals AI |
long context instruction
| AA-LCR | 69.7 % | independent | Artificial Analysis | |
| IFBench | 75.9 % | independent | Artificial Analysis | |
| MultiChallenge | 75.5 % 71.5–79.6 | independent | Scale Labs |
multimodal
| MMMU implementation=vals-ai | 87.4 % | independent | Vals AI |
professional
| CaseLaw | 63.1 % | independent | Vals AI | |
| CorpFin | 65.1 % | independent | Vals AI | |
| LegalBench | 84.2 % | independent | Vals AI | |
| TaxEval | 77.7 % | independent | Vals AI |
reasoning math
| AIME implementation=vals-ai | 96.9 % | independent | Vals AI | |
| FrontierMath | 39.0 % | independent | Epoch AI Benchmarking Hub 2026-04-08 | |
| FrontierMath Tier 4older version | 14.6 % | independent | Epoch AI Benchmarking Hub 2026-04-08 | |
| OTIS Mock AIME 2024–2025 | 88.9 % | independent | Epoch AI Benchmarking Hub 2026-04-08 |
Agent + model results
systems, not bare-model scores
| agent + model Artificial Analysis harness + Muse Spark | Terminal-Bench 2.1 | 62.2 % | independent | Artificial Analysis |
| agent + model Artificial Analysis harness + Muse Spark | Terminal-Bench Hard | 45.5 % | independent | Artificial Analysis |
These scores measure the whole agent system (scaffold, tools, budgets) — they are never merged into the bare model’s numbers.
