LLMs TigerLive LLM benchmarks

Muse Spark 1.1 (xhigh): benchmark scores, price and ranking

Muse Spark 1.1 (xhigh) from Meta AI ranks #66 of 743 LLMs on the LLMs Tiger aggregate benchmark score (52.4), based on 2 benchmark results captured up to 2026-10-13.

Organisation
Meta AI
Type
Frontier model
Open weights
No
Released
2026-07-09 (source: epoch)
Cheapest API price
$1.25 in / $4.25 out per million tokens (via meta, observed 2026-10-13T20:47Z)
Aggregate rank
#66 of 743 (score 52.4)

Across the 2 benchmarks where at least ten models are scored, Muse Spark 1.1 (xhigh) is in the top 10% on 1 and in the top half on 2.

Its cheapest listed input price, $1.25 per million tokens, is lower than that of 26% of the 427 models with a listed price.

Muse Spark 1.1 (xhigh) benchmark results

Muse Spark 1.1 (xhigh) benchmark scores, ranked against all models measured on each benchmark
BenchmarkScoreRankSourceCaptured
SciCode58.8%#9 of 106Epoch AI Benchmarking Hub2026-10-13
CritPt15.1%#29 of 115Epoch AI Benchmarking Hub2026-10-13

About Muse Spark 1.1 (xhigh)

Muse Spark 1.1 (xhigh) is a frontier model from Meta AI. It was released on 2026-07-09, according to Epoch AI. The cheapest API listing we track charges $1.25 per million input tokens and $4.25 per million output tokens, through meta. We hold 2 benchmark results for it across 2 areas, and 1 is in the top tenth of its board.

Where Muse Spark 1.1 (xhigh) stands

On our aggregate score, Muse Spark 1.1 (xhigh) is #66 of 743 ranked models, in the top quarter. Its score is 52.4; the scale is centred on 50, so it sits 2.4 points above the typical model. That beats 91% of the ranked field. Among the 28 ranked Meta AI models it is #3. The next one up is Muse Spark at 53.7. The next one down is Muse Spark 1.2 (xhigh) at 51.5.

Muse Spark 1.1 (xhigh), benchmark by benchmark

On SciCode, Muse Spark 1.1 (xhigh) scores 58.8% and ranks #9 of 106. Only 8 models score higher, led by Claude Opus 5.5 (max) at 66.9%, which is 8.1 points ahead. It covers scientific research code. The board median is 44.3%, so Muse Spark 1.1 (xhigh) is 14.5 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

On CritPt, Muse Spark 1.1 (xhigh) reaches 15.1%. It ranks #29 of 115, ahead of 75% of the field, and 17.1 points behind GPT-5.6 Sol (max) at 32.3%. The results either side are Grok 4.5 (high) (15.4%) and deepseek-v4.1-flash-max (14.3%). It covers unpublished research-level physics problems. The board median is 2.9%, so Muse Spark 1.1 (xhigh) is 12.3 points above it. Source: Epoch AI Benchmarking Hub, captured 2026-10-13.

Strengths and weaknesses

Muse Spark 1.1 (xhigh) has too few results on boards with ten or more models to say where it is strong or weak. Treat any single score as a data point, not a verdict.

Price and value

The median input price across the 427 priced models is $0.500 per million tokens, so Muse Spark 1.1 (xhigh) costs more than the typical listing. Models that score within 1.5 points or better and cost less: DeepSeek V4 Flash 0731 (max) ($0.016, 53.1), GLM-5.2 (high) ($0.060, 51.6), Qwen3-Coder-30B-A3B-Instruct ($0.070, 52.7). Similar scores cost more on glm-5p1 ($1.40) and gemini-3.5-flash-high ($1.50).

Release history

The Meta AI model released before it was Muse Spark on 2026-04-08, which scores 53.7. The next one was Muse Spark 1.2 (xhigh) on 2026-08-05, at 51.5.

Reading these numbers

The 2 scores on this page come from 1 source: Epoch AI Benchmarking Hub (2). No official leaderboard supplied any of them, so treat them as third-party measurements. The leaderboard also lists 3 other reasoning-effort settings of this model, which redirect here. This page shows the highest. With 2 results the aggregate rank can move a lot when one new score arrives.

Muse Spark 1.1 (xhigh) is also listed at 3 other reasoning-effort settings; this page shows the highest-effort row, which is the one the leaderboard keeps by default.

Models ranked nearby

More from Meta AI

Compare it on the live leaderboard → · How the aggregate score works