Meta AI·released 2026-07-091 source
Muse Spark 1.1 benchmark scores: 7 benchmarks tracked. 0% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 7 benchmarks·best result 90.67 on DTBench (unverified)·0 of 7 independently reproduced
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| DTBench | 90.67accuracy (%) | unverifiedT1 | 2026-07-09https://conceptualreasoning.ai/dtbench |
| LMCA | 58.72accuracy (%) | unverifiedT1 | 2026-07-09https://conceptualreasoning.ai/lmca |
| SimpleQA Verified | 57.79accuracy (%) | unverifiedT2 | 2026-07-09 |
| DeepSWE | 53.32accuracy (%) | unverifiedT1 | 2026-07-09https://deepswe.datacurve.ai/ |
| Surface Evolver Bench | 52.5accuracy (%) | unverifiedT1 | 2026-07-09https://yhenon.github.io/surface-evolver-llm-eval/ |
| ProofBench | 39accuracy (%) | unverifiedT1 | 2026-07-09https://www.vals.ai/benchmarks/proof_bench |
| APEX-Agents | 31.8accuracy (%) | unverifiedT2 | 2026-07-09 |
Claims drawn from cited facts, not live model generation.
This model was developed by Meta AI and released in 2026.
2 cited facts
This model has scores on 7 tracked benchmarks and currently leads 0 of them. The record’s evidence status is unverified.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 31.74 points.
1 cited fact
1 facts cross-checked across data sources: 1 single-source.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks
Muse Spark 1.1 is an AI model developed by Meta AI, released 2026-07-09. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
Muse Spark 1.1 has recorded scores on 7 benchmarks, each shown with its evidence status.
Muse Spark 1.1 has recorded scores on 7 benchmarks — DTBench, LMCA, SimpleQA Verified, APEX-Agents, Surface Evolver Bench, DeepSWE, and 1 more. The full table above shows each score with its evidence status.
0 of 7 recorded scores (0%) are independently reproduced rather than self-reported by the lab.
Muse Spark 1.1 has 7 tracked claims: 7 unverified.