Automated page. Written and translated automatically by AI and checked against the sources by software; no human editor. SI-IQ is an index built from public benchmark results, not an IQ test. How it works

How smart is Muse Spark Open?

127 SI-IQ · 90% interval 124–130
Rank 22 of 80 ranked models · Plausible rank range 13–40

Muse Spark Open is a model from Meta AI, released on Oct 15, 2026. Its SI-IQ is 127 (90% interval 124–130), estimated from 7 benchmark results by 2 evaluators.

Data as of Oct 18, 2026 · method 1.0.0

Facts

Developer
Meta AI
Released
Oct 15, 2026
Access
Open weights (restricted licence)
Benchmarks used
7 benchmark results from 2 evaluators

Ability by area (SI-IQ, 90% interval)

6080100120140160Math127Knowledge128

Every benchmark result we used

Each score is one value exactly as the source published it: for Epoch AI the best of its run settings, for OpenRouter the median hosting provider (the developer's own hosting when it ran the test). “Implied SI-IQ” is the ability that this single result points to; the overall SI-IQ is their precision-weighted average.

Benchmark Area Score Implied SI-IQ Evaluated by As listed by the source Retrieved Source
FrontierMath Tier 4 Math 31.7% 126 Epoch AI Muse-Spark-Open-816B-A42B_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
FrontierMath Tiers 1–3 Math 69.8% 128 Epoch AI Muse-Spark-Open-816B-A42B_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
OTIS Mock AIME 2024–2025 Math 98.1% 131 Epoch AI Muse-Spark-Open-816B-A42B_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond Knowledge 88.6% 121 Epoch AI Muse-Spark-Open-816B-A42B_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
GPQA Diamond (OpenRouter run) Knowledge 90.6% 131 OpenRouter meta/muse-spark-open-20261015
Fireworks · median over providers (1 of 1 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file
SimpleQA Verified Knowledge 56.6% 135 Epoch AI Muse-Spark-Open-816B-A42B_xhigh Oct 18, 2026 Epoch AI Benchmarking Hub · data file
τ²-bench Airline (OpenRouter run) Agents 78.0% 135 OpenRouter meta/muse-spark-open-20261015
Fireworks · median over providers (1 of 1 rows)
Oct 18, 2026 OpenRouter benchmark datasets · data file

Models with similar SI-IQ

ModelSI-IQ
Kimi K3Moonshot127Muse Spark Open vs Kimi K3
Claude Opus 4.7Anthropic127Muse Spark Open vs Claude Opus 4.7
Gemini 3.1 ProGoogle DeepMind127Muse Spark Open vs Gemini 3.1 Pro
DeepSeek V4 Pro 0813DeepSeek128Muse Spark Open vs DeepSeek V4 Pro 0813
DeepSeek V4.1 FlashDeepSeek128Muse Spark Open vs DeepSeek V4.1 Flash

Computed with SI-IQ method version 1.0.0. Read the full methodology

Data sources: Epoch AI, ‘Capabilities & benchmarking’ (CC BY 4.0); Source: OpenRouter (openrouter.ai), licensed under CC BY 4.0: reuse and republish with attribution to OpenRouter (licences and changes).