GPT-5.1 vs Muse Spark

Verdict

Muse Spark leads 5–0 across 5 shared benchmarks.

GPT-5.1 0 · Muse Spark 5 · higher isn't always better — check the caveats below.

Per-benchmark head-to-head

Reported scores — protocols may differ. How we compare

Sort

GPT-5.1Muse Spark

54.45
AFrontierMath-2025-02-28-Private
68.42
20.83
AFrontierMath-Tier-4-2025-07-01-Private
24.33
83.5
BGPQA diamond
86.4
19.83
AHLE
37.56
88.6
BOTIS Mock AIME 2024-2025
88.89

Capabilities

Math

Math: Muse Spark leads 3–0 across 3 shared math benchmarks (largest gap: FrontierMath-2025-02-28-Private, 68.42 vs 54.45 — single evaluator).

6 reproduced

Reasoning

Reasoning: Muse Spark leads 2–0 across 2 shared reasoning benchmarks (largest gap: HLE, 37.56 vs 19.83 — protocols undisclosed).

2 reproduced2 unverified

A higher score does not always mean a better model. Each number is task performance under a disclosed harness. Of the 10 measurements across 5 shared benchmarks, 10 single-evaluator or undisclosed-protocol reports; 80% are independently reproduced. GPT-5.1 pricing is cross-check disputed — weigh cost claims with the same caution as benchmark wins. Check any benchmark's integrity grade before reading a win as decisive.

Frequently asked questions

Muse Spark leads 5–0 across 5 shared benchmarks. GPT-5.1 leads 0 benchmarks and Muse Spark leads 5. Higher isn't always better — see the integrity caveats on each benchmark.

GPT-5.1 and Muse Spark have 5 benchmarks in common in our data — those are the only rows where a direct, apples-to-apples comparison is drawn.

Muse Spark leads math 3–0. Muse Spark leads reasoning 2–0.

Follow the record

These models

Same tier