EnterpriseOps-Gym-AA ↗47.27%
Muse Spark 1.2 (Xhigh) · EnterpriseOps-Gym-AA ↗
Meta / MODEL EVIDENCE
Muse Spark 1.2
44 benchmarks · 47 observations · 45 sources · released 2026-08-05
Scores at a glance
44 benchmarks · large dot: Muse Spark 1.2; small dots: closest models where reported
ErdősBench ↗2.730 / 4
Muse Spark 1.2 · ErdősBench · mean progress / 4 · API ↗
SimpleQA Verified ↗60.3%
Muse Spark 1.2 (xhigh) · SimpleQA Verified · Best score (across scorers) · % ↗
Muse Spark 1.2 (xhigh) · Chess Puzzles · Best score (across scorers) · % ↗
SimpleBench ↗74.5%
Muse Spark 1.2 · SimpleBench · Score (AVG@5) · % ↗
WeirdML (v2) ↗60.3%
Muse Spark 1.2 (xhigh) · WeirdML · Accuracy · % ↗
Muse Spark 1.2 · APEX-Agents · Pass@1 score · % ↗
CritPt ↗17.71%
Muse Spark 1.2 (xhigh) · CritPt · Accuracy · % ↗
DeepSWE v1.1 ↗54.87%
Muse Spark 1.2 (xhigh) · DeepSWE · Pass@1 · % ↗
ProofBench ↗43 %
Muse Spark 1.2 · ProofBench · Accuracy ↗
1 more reported result
43% · Muse Spark 1.2 · ProofBench · Accuracy · % · Epoch AI · ProofBench ↗
LMCA ↗48.35%
Muse Spark 1.2 (xhigh) · LMCA · Score · % ↗
DTBench ↗94.67%
Muse Spark 1.2 (xhigh) · DTBench · Accuracy · % ↗
GDP.pdf ↗12%
Muse Spark 1.2 · GDP.pdf · GDP.pdf score · % ↗
1 more reported result
16% · Muse Spark 1.2 (xhigh) · GDP.pdf · GDP.pdf score · % · Epoch AI · GDP.pdf ↗
FrontierSWE v2 ↗11.97%
Muse Spark 1.2 (xhigh) · FrontierSWE · Score · % ↗
SciCode ↗57.41%
Muse Spark 1.2 (xhigh) · SciCode · Score · % ↗
Text Arena (Coding) ↗1534.38 Elo
Muse Spark 1.2 (xhigh) · WebDev Arena · Elo ↗
Epoch Capabilities Index (ECI) ↗155.05 ECI
Muse Spark 1.2 · General ECI · 26 October 2026 fit ↗
Vals Multimodal Index ↗69.8 %
Muse Spark 1.2 · Vals Multimodal Index · Accuracy ↗
Legal Research Bench ↗43.75 %
Muse Spark 1.2 · Legal Research Bench · All-Pass ↗
LegalBench ↗85.26 %
Muse Spark 1.2 · LegalBench · Accuracy ↗
Muse Spark 1.2 · Harvey's Legal Agent Benchmark v1 · Accuracy ↗
Tax Agent Bench ↗32.8 %
Muse Spark 1.2 · Tax Agent Bench · Accuracy ↗
Vals Finance Agent v2 ↗60.6 %
Muse Spark 1.2 · Finance Agent v2 · Accuracy ↗
Muse Spark 1.2 · Excel Modeling Benchmark v1 · Accuracy ↗
CorpFin v2 ↗70.94 %
Muse Spark 1.2 · CorpFin · Accuracy ↗
MortgageTax & TaxEval v2 ↗65.42 %
Muse Spark 1.2 · MortgageTax · Accuracy ↗
1 more reported result
80.38 % · Muse Spark 1.2 · TaxEval · Accuracy · Vals AI · TaxEval ↗
MedCode ↗49.35 %
Muse Spark 1.2 · MedCode · Accuracy ↗
MedScribe ↗90.06 %
Muse Spark 1.2 · MedScribe · Accuracy ↗
BioMysteryBench ↗64.81 %
Muse Spark 1.2 · BioMysteryBench · Accuracy ↗
MMLU-Pro ↗88.28 %
Muse Spark 1.2 · MMLU Pro · Accuracy ↗
MMMU-Pro ↗86.13 %
Muse Spark 1.2 · MMMU Pro · Accuracy ↗
Muse Spark 1.2 · SAGE · Accuracy ↗
Vibe Code Bench ↗79.1 %
Muse Spark 1.2 (OpenHands) · Vibe Code Bench · original task set ↗
ProgramBench ↗0.5 %
Muse Spark 1.2 · ProgramBench · Accuracy ↗
Terminal-Bench 4.0 ↗6.06 %
Muse Spark 1.2 (Mini-SWE-agent) · Terminal-Bench 4.0 · Score ↗
SkillsBench ↗53.04 %
Muse Spark 1.2 (OpenHands) · SkillsBench · Score ↗
IOI v1 & IOI v2 ↗21.78 %
Muse Spark 1.2 · IOI · Accuracy ↗
Code Migration v1.1 ↗29.95 %
Muse Spark 1.2 · Code Migration v1 · Accuracy ↗
SWE-bench Verified ↗86.6 %
Muse Spark 1.2 (Mini-SWE-agent) · SWE-bench Verified · Score ↗
CyberBench v1.1 ↗69.52 %
Muse Spark 1.2 · CyberBench · Accuracy ↗
SRE-Bench ↗0 %
Muse Spark 1.2 · SRE Bench · Accuracy ↗
Public Benefits Bench v1.1 ↗68.47 %
Muse Spark 1.2 · Public Benefits Bench · Accuracy ↗
Muse Spark 1.2 (xhigh) · Humanity's Sixth Sense · Score ↗
DistressBench ↗88.39%
muse-spark-1.2 · DistressBench · Score ↗
Closest models by score
Similar positions on shared benchmark leaderboards. Smaller gaps are closer.
Kimi K3 →Kimi
24 of 31 shared benchmark comparisons
Grok 4.6 →xAI
22 of 31 shared benchmark comparisons
Claude Opus 4.8 →Anthropic
22 of 31 shared benchmark comparisons
How similarity is measured
Mean absolute gap in percentile positions on shared benchmark settings; lower is closer. At least 60% overlap is required, with a minimum of three when available. Independent evaluations are used when there are at least three; otherwise published report comparisons are used. Repeated model observations within one setting are averaged before ranking. Writing-style traits and composite indices are excluded. This describes similarity, not an overall quality ranking.
Sources
Every plotted observation links to its evaluation. Reported configurations, benchmark versions and task subsets can differ; similarity describes shared scores, not training lift.
- Arena leaderboard — WebDev evaluation ↗
- EnterpriseOps-Gym-AA Benchmark | Artificial Analysis ↗
- SciCode Benchmark | Artificial Analysis ↗
- DTBench — Conceptual Reasoning Index ↗
- LMCA — Conceptual Reasoning Index ↗
- DeepSWE ↗
- APEX-Agents ↗
- Chess Puzzles ↗
- CritPt v1 ↗
- SimpleQA Verified ↗
- AI benchmarks & capabilities ↗
- WeirdML ↗
- DistressBench — evaluation methodology and results ↗
- Humanity's Sixth Sense — evaluation methodology and results ↗
- AI Model Benchmarks — LM Council ↗
- GDP.pdf Benchmark | Surge AI ↗
- FrontierSWE — software engineering benchmark ↗
- ErdősBench: research mathematics, scoped progress and proof audits ↗
- BioMysteryBench — evaluation methodology and results ↗
- Code Migration v1 — evaluation methodology and results ↗
- CorpFin — evaluation methodology and results ↗
- CyberBench — evaluation methodology and results ↗
- Excel Modeling Benchmark v1 — evaluation methodology and results ↗
- Finance Agent v2 — evaluation methodology and results ↗
- Harvey's Legal Agent Benchmark v1 — evaluation methodology and results ↗
- IOI — evaluation methodology and results ↗
- LegalBench — evaluation methodology and results ↗
- Legal Research Bench — evaluation methodology and results ↗
- MedCode — evaluation methodology and results ↗
- MedScribe — evaluation methodology and results ↗
- MMLU Pro — evaluation methodology and results ↗
- MMMU Pro — evaluation methodology and results ↗
- MortgageTax — evaluation methodology and results ↗
- ProgramBench — evaluation methodology and results ↗
- ProofBench — evaluation methodology and results ↗
- Public Benefits Bench — evaluation methodology and results ↗
- SAGE — evaluation methodology and results ↗
- SkillsBench — evaluation methodology and results ↗
- SRE Bench — evaluation methodology and results ↗
- SWE-bench Verified — evaluation methodology and results ↗
- Tax Agent Bench — evaluation methodology and results ↗
- TaxEval — evaluation methodology and results ↗
- Terminal-Bench 4.0 — evaluation methodology and results ↗
- Vals Multimodal Index — evaluation methodology and results ↗
- Vibe Code Bench — evaluation methodology and results ↗
Names used in source tables
Muse Spark 1.2 · Muse Spark 1.2 (Mini-SWE-agent) · Muse Spark 1.2 (OpenHands) · Muse Spark 1.2 (Xhigh) · Muse Spark 1.2 (xhigh) · muse-spark-1.2