Muse Spark 1.3: score and benchmark evidence
Historical release · · Meta
104.0 points · Rank 10 among 19 ranked models · Stability range 91.3–117.8 points.
Rank follows the point estimate; it does not establish statistically significant superiority. The scale is anchored at mean 100, SD 15 in the frozen calibration cohort, not human IQ or a percentage.
One capability score combines evidence across seven equally weighted domains. Related benchmark variants share a family budget, and influence from one evaluator is capped.
Release tli-2026-v5.1-2026-09-06. Methodology and limitations for this release.
This page preserves historical evidence. See the current model record.
Capability domains
Domain scores use calibration-cohort standard-deviation units. Unmeasured domains are shown as unavailable, not zero.
| Domain | Score (SD units) | Observed benchmarks |
|---|---|---|
| Knowledge & reasoning | 0.31 | 2 |
| Coding & software engineering | 0.11 | 1 |
| Agentic tool & computer use | 0.06 | 2 |
| Professional & real-world work | 0.13 | 1 |
| Multimodal & vision | -0.05 | 2 |
| Cybersecurity | Unavailable | 0 |
| Preference & communication | Unavailable | 0 |
Published benchmark evidence
8 results contribute to this score, from 23 collected results and 8 contributing benchmark families. Counts are not independent sample sizes.
Only results with a matched source record, metric and documented configuration contribute. Developer-reported results are eligible when their configuration is clear. Unresolved records remain in the database with their exclusion reason. Archived reviews and live source checks are labelled separately.
The bar estimates score stability under the scoring assumptions: a fixed calibration and comparable benchmark availability. It resamples benchmark families and evaluators while keeping each domain’s evidence strength fixed, then adds a frozen correction learned from missing-evidence tests. Benchmark count and domain coverage both affect that correction. It does not add a second full capability-posterior draw or uncertainty from changing the reference calibration. It is not a guarantee under selective publication, new benchmark domains or future model releases.
Reporting sensitivity: ±22.6 points. Sensitivity to selectively published results. This stress range is not a confidence interval or a probability statement.
GDPval-AA v2 (Elo): 1709 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: muse-spark-1.3; xhigh effort; Artificial Analysis agent harness
Metric: Elo rating
Original source · Retrieved 2026-09-03T00:00:00.000Z
Exact-value match to an existing verified, comparable, pinned-configuration observation. Archived review retained; not asserted newly independently replicated.
Terminal-Bench 2.1: 89.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
DeepSWE v1.1: 75.4%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
AA Intelligence Index v4.1.1 (score): 61 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Held-out composite, never a scoring input
GPQA Diamond: 94%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
AA-LCR: 79%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
SciCode: 59%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
Humanity's Last Exam (no tools): 47%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
AutomationBench v1.0.6: 43.8%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
AA-Omniscience: 23.1 native-points
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Muse Spark 1.3 (xhigh); AA published evaluation harness
Metric: AA Omniscience index -100 to 100
Original source · Retrieved 2026-09-06
Current first-party evaluator data matches the recorded score at its published rounding. Exact pinned configuration selected; later value changes are not silently substituted.
LiveBench: 81.59%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
MMMU-Pro: 82.02%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Muse Spark 1.3 (xhigh); AA published evaluation harness
Metric: accuracy, AA
Original source · Retrieved 2026-09-06
Current first-party evaluator data matches the recorded score at its published rounding. Exact pinned configuration selected; later value changes are not silently substituted.
OSWorld 2.0 — Anthropic H2H: 66.9%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
JobBench: 61.2%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
τ³-Banking: 47.2%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Muse Spark 1.3 (xhigh); AA published evaluation harness
Metric: strict task success, AA
Original source · Retrieved 2026-09-06
Current first-party evaluator data matches the recorded score at its published rounding. Exact pinned configuration selected; later value changes are not silently substituted.
CritPt: 26%
Contributes to the score. Source category: independent. Review status: reviewed-independent.
Configuration: Muse Spark 1.3 (xhigh); AA published evaluation harness
Metric: accuracy, AA official grading
Original source · Retrieved 2026-09-06
Current first-party evaluator data matches the recorded score at its published rounding. Exact pinned configuration selected; later value changes are not silently substituted.
MineBench: 1836 native-points
Not used in the score. Source category not recorded. Review status: excluded.
Unresolved Pro/base model identities in source catalog; exclude until matched.
OSWorld 2.0: 32%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
Harvey LAB-AA: 95.48%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
Tax Agent Bench v1 — Vals: 71.934%
Not used in the score. Source category not recorded. Review status: unresolved.
Inherited cell lacks a matched, reviewed source/configuration record.
RuneBench (30m, mean ln(1 + XP/min)): 4.58575 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: muse13
Metric: Arithmetic mean of ln(1 + peakXpRate) over all 16 skills, exactly as the owner’s Heatmap.js default ranking. Data rates are already normalized; do not divide by 200 again.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Roboflow Vision Evals (six-task mean, high tier): 77.733333%
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: Require a complete six-task high-tier panel, the highest published benchmark tier. Retain high-tier scores even when lower than low-tier. Do not substitute the best of three repetitions: use the published mean. Each panel enters the fit once; do not also fit its components.
Metric: Arithmetic mean of six published high-tier task means; derived by The Latent, not Roboflow’s official low-tier overall score.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Code Arena WebDev (overall): 1622 native-points
Contributes to the score. Source category: independent. Review status: reviewed-archive.
Configuration: muse-spark-1.3 (xHigh)
Metric: Published overall WebDev preference rating, not task success percentage or Arena Text score.
Original source · Retrieved 2026-09-06
Matched exact metric/value and the archived benchmark-specific configuration review. Unknown native effort stays explicitly unknown.
Cite this model record
The Latent. “Muse Spark 1.3: score and benchmark evidence.” 2026-09-06. Release tli-2026-v5.1-2026-09-06.
Download release data and definitions (JSON) · Data usage terms