RankingEffort benchmarks

Muse Wonder

Compare models

43 measured results · 1 effort settings · 43 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 Wonder · Max4 of 7 capabilities supported

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

Agentic
A76.1Supported
Hard reasoning
A68.9Supported
Coding
A78.2Supported
Human pref
Unknown
Knowledge
A42.4Supported
Multimodal
Unknown
Long context
A57.3Preliminary

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 Wonder · Max: 73.2 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 · 43.7% direct comparison weight · independent of the model provider
LiveBench · 30.5% direct comparison weight · independent of the model provider
Vals AI · 25.9% direct comparison weight · independent of the model provider

Which benchmark families carry the weight?

harvey · 7.0% direct comparison weight
Humanity’s Last Exam · 4.8% direct comparison weight
Critpt · 4.8% direct comparison weight
omniscience · 4.8% direct comparison weight
Aa Lcr · 4.7% direct comparison weight
Other families (18) · 73.9% 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.

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	35 → 40	Down 5	203 remaining / 241 lost	72.2 (-1.0 points)
ARC Prize	35 → 35	No movement	444 remaining / 0 lost	76.2 (+3.0 points)
Datacurve	35 → 34	Up 1	444 remaining / 0 lost	70.3 (-2.9 points)
LiveCodeBench	35 → 35	No movement	444 remaining / 0 lost	73.2 (-0.0 points)
Scale	35 → 37	Down 2	444 remaining / 0 lost	73.9 (+0.6 points)
Terminal-Bench	35 → 33	Up 2	444 remaining / 0 lost	73.3 (+0.1 points)
Cognition	35 → 29	Up 6	444 remaining / 0 lost	73.0 (-0.2 points)
LiveBench	35 → 28	Up 7	443 remaining / 1 lost	77.7 (+4.5 points)
SWE-rebench	35 → 35	No movement	444 remaining / 0 lost	72.8 (-0.5 points)
Epoch AI	35 → 38	Down 3	431 remaining / 13 lost	73.5 (+0.3 points)
Vals AI	35 → 40	Down 5	443 remaining / 1 lost	70.7 (-2.5 points)
Provider reports · Anthropic	35 → 36	Down 1	444 remaining / 0 lost	73.1 (-0.1 points)
Provider reports · Moonshot AI	35 → 35	No movement	444 remaining / 0 lost	72.9 (-0.3 points)
Provider reports · Meta	35 → 36	Down 1	444 remaining / 0 lost	72.8 (-0.4 points)
Provider reports · Mistral	35 → 35	No movement	444 remaining / 0 lost	73.2 (+0.0 points)
Provider reports · OpenAI	35 → 35	No movement	444 remaining / 0 lost	73.1 (-0.1 points)
All provider reports	35 → 36	Down 1	444 remaining / 0 lost	72.3 (-0.9 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
deepswe	70.3	-2.9
arc-agi	75.1	+1.9
omniscience	74.9	+1.7
livebench-language	74.7	+1.5
harvey	71.8	-1.4
multi-swe-bench	71.9	-1.3
livebench-math	72.3	-0.9
aa-lcr	73.9	+0.7
mmmu-pro	73.9	+0.7
vals-code-migration	72.5	-0.7
vals-legal-research	72.6	-0.7
hle	73.8	+0.6
vals-excel-modeling	73.8	+0.6
briefcase	72.7	-0.5
swe-rebench	72.8	-0.5
automationbench	72.8	-0.5
mmlu-pro	73.6	+0.4
livebench-coding	73.6	+0.4
gdpval	72.9	-0.3
vals-finance-agent	73.5	+0.3
terminal-bench	73.5	+0.3
epoch-game-puzzles	72.9	-0.3
swe-atlas-test-writing	72.9	-0.3
critpt	73.5	+0.3
livebench-instructions	73.5	+0.3
ifbench	72.9	-0.3
simpleqa	73.4	+0.2
frontiercode	73.0	-0.2
tau-bench	73.0	-0.2
swe-atlas-qna	73.0	-0.2
arc-agi-3	73.0	-0.2
gdp-pdf	73.0	-0.2
gpqa	73.1	-0.2
livebench-data	73.3	+0.1
vals-tax-agent	73.1	-0.1
livebench-reasoning	73.1	-0.1
itbench	73.3	+0.1
analyst-agent	73.3	+0.1
vibe-code	73.3	+0.1
terminal-bench-science	73.3	+0.1
swe-atlas-refactoring	73.2	-0.1
frontiermath	73.2	-0.1
enterprise-ops	73.3	+0.0
apex-agents	73.2	+0.0
aime	73.2	-0.0
enigma-eval	73.2	-0.0
livecodebench	73.2	-0.0
swe-bench-pro	73.2	+0.0
gmmlu	73.2	-0.0
math500	73.2	+0.0

What evidence is missing from the fit?

Across all collected settings for this model: 46 observations, 40 contributing, 0 matched without graph weight and 6 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
1 · Evaluator has not been reviewed for independent admission
3 · Supporting evidence outside the reviewed capability core

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	Max
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.	1,658.65 Elo Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	80.67% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	68.09% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	28.29% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	30.6% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	1,770.34 Elo Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
Harvey LAB-AA v1.1: Hallucination-Gated All-Pass RateArtificial Analysis · Stirrup; Harvey private dataset v1.1.0; 120 tasks across 24 practice areas; up to 200 turns; internet disabled; GPT-6 Sol, Grok 4.7 and Claude Opus 5.5 rubric judges; GPT-6 Sol High two-pass hallucination check; hallucination-gated all-pass averaged across judges Benchmark details Average over tasks of the share of the judge panel finding every rubric criterion passed, with a task zeroed on any material hallucination · Independently benchmarked by Artificial Analysis · Evaluation results measured independently by Artificial Analysis Unit: percent. Source collected 2026-10-18.	10% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	50.09% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	25.48 Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	41.1% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	60.3% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	52.02% Reported settings Muse Wonder (Max); Model source: https://artificialanalysis.ai/models/muse-wonder
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.	99% Reported settings LiveBench official task evaluation; livebench-2026-06-25-AMPS_Hard; muse-wonder-1.0-max; checkpoint=muse-wonder
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-wonder-1.0-max; checkpoint=muse-wonder
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.	83.1% Reported settings LiveBench official task evaluation; livebench-2026-06-25-code_generation; muse-wonder-1.0-max; checkpoint=muse-wonder
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.	96% Reported settings LiveBench official task evaluation; livebench-2026-06-25-connections; muse-wonder-1.0-max; checkpoint=muse-wonder
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.	98.53% Reported settings LiveBench official task evaluation; livebench-2026-06-25-consecutive_events; muse-wonder-1.0-max; checkpoint=muse-wonder
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.	98% Reported settings LiveBench official task evaluation; livebench-2026-06-25-integrals_with_game; muse-wonder-1.0-max; checkpoint=muse-wonder
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.	68.18% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-javascript; muse-wonder-1.0-max; checkpoint=muse-wonder
LiveBench · logic with navigation · 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.	80% Reported settings LiveBench official task evaluation; livebench-2026-06-25-logic_with_navigation; muse-wonder-1.0-max; checkpoint=muse-wonder
LiveBench · math comp · 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.	97.06% Reported settings LiveBench official task evaluation; livebench-2026-06-25-math_comp; muse-wonder-1.0-max; checkpoint=muse-wonder
LiveBench · olympiad · 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.	91.82% Reported settings LiveBench official task evaluation; livebench-2026-06-25-olympiad; muse-wonder-1.0-max; checkpoint=muse-wonder
LiveBench · paraphrase · 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.	74.07% Reported settings LiveBench official task evaluation; livebench-2026-06-25-paraphrase; muse-wonder-1.0-max; checkpoint=muse-wonder
LiveBench · plot unscrambling · 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.	74.8% Reported settings LiveBench official task evaluation; livebench-2026-06-25-plot_unscrambling; muse-wonder-1.0-max; checkpoint=muse-wonder
LiveBench · python · 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.	60% Reported settings LiveBench Mini-SWE-Agent, 250-step limit; livebench-2026-06-25-python; muse-wonder-1.0-max; checkpoint=muse-wonder

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 Wonder

Compare with

One configuration, seven capabilities

Agentic

Hard reasoning

Coding

Human pref

Knowledge

Multimodal

Long context

Capability score evidence

Benchmark results