RankingEffort benchmarks

Muse Spark 1.1 · XHigh

Compare models

52 measured results · 2 effort settings · 52 benchmark/harness combinations

Model evidence and sources →

Change model

Model

Current configurationSources

Compare with

Choose a second model and its effort to see both profiles and benchmark differences below.

Compare withModel and configuration

Capability profile

One configuration, seven capabilities

Comparison score · 0–100

AMuse Spark 1.1 · XHigh4 of 7 capabilities supported

Gaps are unknown, not zero. Hollow points are preliminary.

Agentic
A51.1Supported
Hard reasoning
A43.3Supported
Coding
A47.0Supported
Human pref
Unknown
Knowledge
A41.7Supported
Multimodal
Unknown
Long context
A39.1Preliminary

Each profile belongs to the named configuration. Capability scores use a shared panel for all axes, distinct from the overall ranking panel; they are not accuracy percentages or direct head-to-head wins.

Capability score evidence

Muse Spark 1.1 · XHigh: 40.2 overall comparison score. Meets the overall evidence requirements.

5 areas measured. The available task mix affects this estimate; missing areas remain unknown.

Which sources carry the weight?

Artificial Analysis · 26.5% direct comparison weight · independent of the model provider
Datacurve · 25.6% direct comparison weight · independent of the model provider
LiveBench · 22.7% direct comparison weight · independent of the model provider
Vals AI · 22.4% direct comparison weight · independent of the model provider
Scale · 2.8% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

DeepSWE · 25.6% direct comparison weight
Terminal-Bench · 5.1% direct comparison weight
livebench-data · 3.2% direct comparison weight
livebench-language · 3.2% direct comparison weight
multi-swe-bench · 3.2% direct comparison weight
Other families (22) · 59.5% direct comparison weight

These shares describe direct comparison weight, not fractions of the final score or confidence. Source balancing does not give every family equal weight or remove correlations between overlapping sources.

DeepSWE v1.1 review: Epoch AI reported grading errors in at least 23 of 113 tasks. These published results remain included. Review their limitations in Epoch's review when interpreting this evidence.

How sensitive is this score?

The audit removes one source at a time and refits against the same overall reference panel. These published results use the matching dataset audited 2026-10-20.

Both ranks use the same surviving configurations for each removal. The cohort starts with 444 configurations supported in the original audit, including separate effort settings. These are diagnostic positions, not the default leaderboard ranks. Eligibility is not rechecked after removal.

What changes when a source is removed?
Removed source	Rank before → after	Rank movement	Cohort remaining / lost support	Score after (change)
Artificial Analysis	79 → 78	Up 1	203 remaining / 241 lost	42.8 (+2.6 points)
ARC Prize	87 → 90	Down 3	444 remaining / 0 lost	44.0 (+3.9 points)
Datacurve	87 → 82	Up 5	444 remaining / 0 lost	38.6 (-1.6 points)
LiveCodeBench	87 → 87	No movement	444 remaining / 0 lost	40.2 (-0.0 points)
Scale	87 → 90	Down 3	444 remaining / 0 lost	40.4 (+0.2 points)
Terminal-Bench	87 → 88	Down 1	444 remaining / 0 lost	40.4 (+0.2 points)
Cognition	87 → 83	Up 4	444 remaining / 0 lost	40.1 (-0.1 points)
LiveBench	87 → 88	Down 1	443 remaining / 1 lost	40.2 (-0.0 points)
SWE-rebench	87 → 87	No movement	444 remaining / 0 lost	39.5 (-0.7 points)
Epoch AI	86 → 86	No movement	431 remaining / 13 lost	41.3 (+1.1 points)
Vals AI	87 → 91	Down 4	443 remaining / 1 lost	37.0 (-3.2 points)
Provider reports · Anthropic	87 → 87	No movement	444 remaining / 0 lost	40.2 (+0.0 points)
Provider reports · Moonshot AI	87 → 86	Up 1	444 remaining / 0 lost	39.8 (-0.4 points)
Provider reports · Meta	87 → 87	No movement	444 remaining / 0 lost	40.2 (+0.0 points)
Provider reports · Mistral	87 → 87	No movement	444 remaining / 0 lost	40.2 (+0.0 points)
Provider reports · OpenAI	87 → 87	No movement	444 remaining / 0 lost	40.2 (+0.0 points)
All provider reports	87 → 86	Up 1	444 remaining / 0 lost	39.9 (-0.3 points)

Lost support means a configuration no longer has a comparison path to the complete reference panel. Its rank is unavailable. A surviving path alone does not establish leaderboard eligibility.

Overlapping sources may remain correlated even with source balancing. Leave-one-source-out movement is a sensitivity diagnostic, not a spread of source-specific ranks or a confidence measure. Scoring methodology · Dated configuration audit

Every benchmark family

Removed evidence	Recomputed score	Change
arc-agi	43.0	+2.8
swe-atlas-test-writing	38.1	-2.1
harvey	38.4	-1.7
deepswe	38.6	-1.6
multi-swe-bench	38.6	-1.6
terminal-bench	41.5	+1.3
mmmu-pro	41.4	+1.2
vals-finance-agent	39.1	-1.1
livebench-language	41.2	+1.0
livebench-math	41.0	+0.8
swe-rebench	39.5	-0.7
vals-excel-modeling	40.9	+0.7
simpleqa	40.9	+0.7
vals-code-migration	40.8	+0.6
hle	40.8	+0.6
briefcase	40.7	+0.5
swe-bench-pro	40.7	+0.5
swe-atlas-refactoring	40.7	+0.5
livebench-reasoning	39.8	-0.4
epoch-game-puzzles	39.8	-0.4
livebench-coding	40.5	+0.3
vals-legal-research	40.5	+0.3
gpqa	39.9	-0.3
swe-atlas-qna	40.5	+0.3
mmlu-pro	40.5	+0.3
tau-bench	39.9	-0.2
ifbench	40.0	-0.2
aime	40.0	-0.2
gdp-pdf	40.4	+0.2
vibe-code	40.4	+0.2
arc-agi-3	40.1	-0.1
aa-lcr	40.3	+0.1
omniscience	40.1	-0.1
frontiercode	40.1	-0.1
livebench-data	40.1	-0.1
critpt	40.1	-0.1
terminal-bench-science	40.3	+0.1
itbench	40.1	-0.1
apex-agents	40.2	+0.0
gdpval	40.2	+0.0
automationbench	40.2	-0.0
livebench-instructions	40.2	-0.0
enigma-eval	40.2	+0.0
livecodebench	40.2	-0.0
enterprise-ops	40.2	-0.0
frontiermath	40.2	-0.0
vals-tax-agent	40.2	+0.0
gmmlu	40.2	+0.0
math500	40.2	+0.0
analyst-agent	40.2	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 77 observations, 45 contributing, 0 matched without graph weight and 32 excluded. Counts do not establish rank eligibility.

1 · Benchmark family or source protocol has not been reviewed
1 · Original SciCode grading defects are under review; retained as supporting evidence, excluded from aggregate and capability scores. Corrected SciCode-Verified requires a separate protocol review. Sources: https://arxiv.org/abs/2608.04975 and https://artificialanalysis.ai/evaluations/scicode
2 · Fewer than two distinct model identities remain in this evaluation
2 · Effort is not identified
1 · Evaluator has not been reviewed for independent admission
19 · No reviewed effort for this catalog observation; any separately collected effort measurement is counted separately
5 · Supporting evidence outside the reviewed capability core
1 · Narrow specialist biological, medical or security evaluation; preserved as raw evidence outside general capability scoring.

Inspect every observation and exclusion →

Benchmark results

These are published benchmark scores. Supported effort estimates also appear on the Capability leaderboard. Results from different harnesses occupy different rows. Missing cells stay unknown; no scores are copied between effort levels.

Benchmark / source	XHigh	Unspecified
AA-Briefcase EloArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Briefcase v1.1 is an agentic knowledge work benchmark developed by Artificial Analysis. AA-Briefcase Elo is a combined metric that aggregates rubric pass rate, analytical quality Elo and presentation Elo · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	850.65 Elo Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
AA-LCR v1.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	77.67% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
AutomationBench-AAArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of task objectives completed with no guardrail violations · Higher is better · Benchmark developed by Zapier · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	38.85% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
CritPtArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Argonne and UIUC, with contributions from 60+ researchers globally. CritPt is under review by its authors following external feedback · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	15.14% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
GDP.pdf: All-pass RateArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Share of attempts where every atomic criterion passed · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	14.4% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
GDPval-AA v2.1 LeaderboardArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Elo rating for performance on real-world work tasks · Anchored to DeepSeek V4.1 Flash (max) at 1600 · Higher is better · Evaluation results measured independently by Artificial Analysis Unit: elo. Source collected 2026-10-18.	1,212.48 Elo Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
GPQA DiamondArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	89.8% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
Humanity's Last ExamArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	46.2% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
AA-Omniscience IndexArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis Unit: index. Source collected 2026-10-18.	28.08 Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
AA-Omniscience AccuracyArtificial Analysis · 6000 questions; 1 attempt; correct-answer share; GPT-5.6 Luna medium grader Benchmark details AA-Omniscience Accuracy (higher is better) measures the proportion of correctly answered questions out of all questions, regardless of whether the model chooses to answer · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	52.05% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
SciCodeArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark curated by scientists across 16 disciplines. SciCode is under review following an independent audit of the dataset · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	58.8% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
𝜏³-BankingArtificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by Sierra Research · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	31.75% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
Terminal-Bench v2.1Artificial Analysis · Artificial Analysis published evaluation; see source for benchmark-specific settings Benchmark details Benchmark developed by the Laude Institute and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	77.9% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
Terminal-Bench v4.0Artificial Analysis · mini-SWE-agent v2.4.6; 66 tasks; pass@1 averaged over 3 repeats; 500 steps; task timeout up to 8 hours Benchmark details Benchmark developed by the Laude Institute, Stanford, and open-source contributors · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	6.06% Reported settings Muse Spark 1.1 (Xhigh); Model source: https://artificialanalysis.ai/models/muse-spark-1-1	Not reported
DeepSWE v1.1Datacurve · mini-swe-agent Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-10-18.	53.3% Reported settings muse-spark-1-1; Reported effort: xhigh; 113 unique tasks; 452 attempts; 4 runs	Not reported
Terminal-Bench 2.1Terminal-Bench · mini-SWE-agent Benchmark details Original public board. Configuration and task coverage may differ; inspect source. Unit: percent. Source collected 2026-10-18.	76.18% Reported settings Muse Spark 1.1; Reported effort: xhigh; 445 trials; recorded 2026-07-09	Not reported
SWE Atlas · QnA · mini-sweScale · mini-swe Benchmark details 124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks. Unit: percent. Source collected 2026-10-18.	42.2% Reported settings 124 code comprehension tasks; strict all-rubrics pass metric; Opus 4.5 judge; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-07-09T21:00:32.000Z; reported margin ±5.08 percentage points; No contamination annotation reported (not proof of absence)	Not reported
SWE Atlas · Test Writing · mini-sweScale · mini-swe Benchmark details 90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks. Unit: percent. Source collected 2026-10-18.	41.48% Reported settings 90 test-writing tasks; execution, mutation checks and rubric judging; source-reported agent harness. Repositories drawn from SWE-bench Pro; distinct tasks.; published row 2026-07-09T21:02:58.000Z; reported margin ±5.96 percentage points; No contamination annotation reported (not proof of absence)	Not reported
LiveBench · AMPS Hard · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	82% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1	Not reported
LiveBench · code completion · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	78.26% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_completion; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1	Not reported
LiveBench · code generation · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	76.06% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1	Not reported
LiveBench · connections · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-connections; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1	Not reported
LiveBench · consecutive events · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	71.09% Reported settings LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1	Not reported
LiveBench · integrals with game · 2026-06-25LiveBench · LiveBench official task evaluation Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	83% Reported settings LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1	Not reported
LiveBench · javascript · 2026-06-25LiveBench · LiveBench Mini-SWE-Agent, 250-step limit Benchmark details LiveBench 2026-06-25 task snapshot. Task scores stay separate and related tasks share their reviewed family budget. Explicit checkpoint and effort labels only. Unit: percent. Source collected 2026-10-18.	77.27% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; muse-spark-1.1-xhigh; checkpoint=muse-spark-1.1	Not reported

What these comparisons mean

Each source reports its own effort labels. Matching labels do not establish equal compute budgets or identical fallback behavior. Open Reported settings to inspect the exact model name, agent and task coverage. Multiple results at one level remain visible rather than selecting the best. Source-reported None or Non-reasoning labels are not treated as evidence that an API supports those settings.

These measurements use their own dated source collection. The leaderboard fits identified configurations jointly; it contains no pooled model ratings. Explicit thinking budgets are separate configurations. Read the methodology.

Download all effort benchmark results · 8,915 results across 259 models · Collected 2026-10-18

Muse Spark 1.1 · XHigh

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results