Atlas

Compare Models

GPT-5.6 Terra vs Muse Wonder

Muse Wonder leads by 2.9 capability points (≈95% interval +0.7 to +5.0): a clear lead over GPT-5.6 Terra · P(higher) ≈ 100%

Wins 107 of 139 shared benchmarks (18 lost, 14 tied)

Capability vs. relative cost
GPT-5.6 TerraMuse WonderClosed weightsOpen weights

Each line runs through one model’s priced reasoning settings, cheapest to most expensive; grey points are other models’ priced settings in the same range. Results whose reasoning effort the source didn’t report are left out wherever a model has named effort levels. Capability and relative cost are the published estimates (relative cost is cost per task as a multiple of GPT-5 (high)); hover a setting, or use the arrow keys, to set it beside the other model’s same setting.

GPT-5.6 TerravsMuse Wondercapability vs. relative costData Nov 15, 2026Village LLM Atlasatlas.village.dev

Benchmark wins18 – 107 · 139 shared, 14 tied

Comparing matching setups only (44 benchmarks excluded) · suites counted once
← GPT-5.6 TerraMuse Wonder →

GPT-5.6 TerravsMuse Wonderwins by categoryData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 23 othersVillage LLM Atlasatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Muse Wonder minus GPT-5.6 Terra.

LisanBench Path LengthGames330327973+76.6
LisanBench Difficulty-WeightedGames11978303+76.1
HPCT Refusal (CAIS)Safety25.097.0+72.0
VCT-Refusal (CAIS)Safety10.760.2+49.5
Harvey's Legal Agent Benchmark - Litigation Dispute ResolutionLegal0.040.0+40.0
Terminal-Bench 4.0 (Artificial Analysis)Code1.538.4+36.9
DeepResearch Bench II (Mercor 130-task set)Search47.210.8−36.4
BioTIER RefusalSafety65.698.7+33.2
ChessBench CoherenceGames69.7100.0+30.3
MindCube TinyMultimodal62.691.1+28.5
Terminal-Bench 4.0Code22.749.5+26.8
GameBench 2Games53.577.8+24.3
HackerRank-BenchCode26.149.7+23.6
APEX-SWECode31.154.6+23.5
GDPval Extended (Mercor held-out rubric score)Professional Work47.270.0+22.8
Humanity's Sixth SenseMultimodal22.743.7+21.0
Harvey LAB (Mercor run, undisclosed ~213-task cohort)Legal2.323.0+20.7
IOI (Vals v2)Code87.666.9−20.7
Harvey's Legal Agent Benchmark - Antitrust CompetitionLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Banking FinanceLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Capital MarketsLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Corporate GovernanceLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Corporate M&ALegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Data Privacy CybersecurityLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Energy Natural ResourcesLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Funds Asset ManagementLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Healthcare Life SciencesLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Intellectual PropertyLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Real EstateLegal0.020.0+20.0
Harvey's Legal Agent Benchmark - Structured Finance SecuritizationLegal20.00.0−20.0
Harvey's Legal Agent Benchmark - Trusts Estates Private ClientLegal0.020.0+20.0
DAYJOB: FinanceFinance & Accounting1.821.3+19.5
HardGeoBench Avg DistanceMultimodal19911369+19.2
SpatialViz-BenchMultimodal65.283.5+18.3
AA-Briefcase v1.1 EloAgents13331659+17.8
DAYJOB: HealthcareHealth & Medicine1.618.0+16.4
Mystery Game PuzzlesGames35.051.0+16.0
Code MigrationCode47.862.6+14.7
DeepSWE v1.1Code64.878.8+14.0
GDPval-AA v2.1Professional Work14611770+13.6
τ³-Banking (Mercor run, bm25_grep retrieval)Agents38.851.9+13.1
Eval Connections One-Shot with TrapsGames86.073.0−13.0
EnigmaEvalGeneral QA23.136.1+13.0
Harvey HLAB — Criteria Pass RateLegal79.892.7+13.0
PCT Political Inconsistency (CAIS)Safety46.233.3+12.9
Terminal-Bench Science 0.1 (Vals)Science10.022.9+12.9
AA-Omniscience IndexIndexes0.125.5+12.7
Vending-Bench 2Games73439432+12.6
Terminal-Bench-Science 0.1Science13.825.7+11.9
Humanity's Last ExamGeneral QA35.947.6+11.7
ERQAMultimodal63.675.3+11.7
Artificial Analysis Intelligence Index v5.0.1Indexes32.343.6+11.2
Artificial Analysis Intelligence Index v4.3.2Indexes42.152.4+10.3
Humanity's Last Exam DiamondGeneral QA28.839.0+10.2
ProofBench v1.1Math74.084.0+10.0
Machiavelli Deception (CAIS)Safety80.483.6−9.7
DistressBenchSafety76.485.9+9.5
Legal Research BenchLegal41.350.5+9.1
CursorBench 4.0Code41.350.4+9.1
IntPhys 2Multimodal61.370.2+8.9
Vibe Code Bench v1.1Code74.683.1+8.5
AutomationBench-AA 1.0.6Agents59.668.1+8.4
MASKSafety93.384.9−8.4
CyberBench v1.1 OverallCybersecurity72.180.4+8.3
Vals Index v2.1Indexes53.161.1+8.0
Public Benefits Bench v1.1Professional Work62.470.2+7.8
Creative Writing v3 EloChat & Writing18562007+7.6
LMArena Text Arena EloChat & Writing14681511+7.5
HardGeoBench Country AccuracyMultimodal45.052.5+7.5
APEX-Accounting 1.1Finance & Accounting59.867.1+7.3
Finance Agent v2 - PrecedentsFinance & Accounting24.832.1+7.2
ChessBench EloGames9251046+7.2
TextQuests Game ProgressGames40.547.6+7.1
LMArena Agent Arena Net Improvement (Steering Burden)Agents-1.81.8+6.8
LMArena Agent Arena Confirmed SuccessAgents-7.25.4+6.3
GDPval (Mercor 213-task rubric score)Professional Work80.787.0+6.3
GDP.pdf (Artificial Analysis, All-pass)Professional Work24.630.6+6.0
Tax Agent BenchFinance & Accounting65.271.2+6.0
APEX-1 (Mercor, mean score)Professional Work69.575.1+5.6
MMMU ProMultimodal79.584.9+5.4
SciCode 1.0.1 (Artificial Analysis)Code55.060.3+5.3
GBENCH One-shot Coding GScoreGames63.358.1−5.3
APEX-Agents 1.1Professional Work71.877.0+5.2
BuseyBench SVGMultimodal6.16.6+5.2
TextQuests Average Cumulative HarmSafety22.220.8+5.0
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & Medicine27.222.2−5.0
Finance Agent v2 - General Quantitative AnalysisFinance & Accounting72.777.6+4.9
NoCoT-Bench NCRI 15.2General QA89.097.7+4.8
MMMU-Pro Extended (Mercor held-out)Multimodal47.443.2−4.2
Artificial Analysis Progress Index v1Indexes324336+4.2
FrontierCode 2.0 (Artificial Analysis)Code23.927.9+4.0
NoCoT-Bench NCKI (kspine v3)General QA104109+4.0
FrontierMath Tiers 1-3 (v2) - PrivateMath86.082.1−3.9
Finance Agent v2 - All PassFinance & Accounting42.845.9+3.2
LiveBench 2.0Agents75.078.1+3.1
BullshitBench v2 LeaderboardSafety54.057.0+3.0
Finance Agent v2 - General Qualitative AnalysisFinance & Accounting67.870.8+3.0
Finance Agent v2 - AdjustmentsFinance & Accounting49.752.7+3.0
Conceptual Reasoning IndexIndexes65.767.7+2.8
Financial Coaching BenchFinance & Accounting71.073.8+2.8
HardGeoBench <=10miMultimodal25.027.5+2.5
HardGeoBench <=100miMultimodal36.338.8+2.5
LMArena Agent Arena Bash ReliabilityAgents0.74.8+2.0
LMCAGeneral QA55.056.8+1.9
DTBenchGeneral QA93.395.2+1.9
ChessBench AccuracyGames71.970.2−1.8
CritPt (avg@5)Science30.028.3−1.7
Creative Writing v3 Rubric ScoreChat & Writing15.916.2+1.6
LMArena Agent Arena Steering BurdenAgents-0.52.6+1.5
CharXiv Extended (Mercor held-out)Multimodal81.179.6−1.5
MMLU ProGeneral QA88.189.6+1.5
ACCoRDGeneral QA74.776.2+1.5
Finance Agent v2 - Market AnalysisFinance & Accounting60.662.1+1.5
CritPt v2 (agentic, avg@5)Science69.771.1+1.4
Epoch Capabilities Index (ECI)Indexes161162+0.9
Finance Agent v2 - ComparablesFinance & Accounting47.047.9+0.9
Excel Modeling BenchmarkFinance & Accounting66.267.1+0.9
LMArena Agent Arena Tool HallucinationAgents1.0-0.5−0.8
SpeciEval (Pooled English Runs)Safety98.197.5−0.6
Finance Agent v2 - Financial ModelingFinance & Accounting23.022.5−0.5
Finance Agent v2 - Earnings AnalysisFinance & Accounting77.376.8−0.5
CharXiv (descriptive and reasoning combined)Multimodal94.194.5+0.4
Finance Agent v2 - Disclosure AnalysisFinance & Accounting66.967.3+0.3
OTIS Mock AIME 2024-2025Math99.799.4−0.3
LMArena Agent Arena Praise vs ComplaintAgents-1.9-1.8+0.1
AA-LCR Extended (Mercor held-out)Search74.474.40.0
FrontierMath Tier 4 (v2) - PrivateMath70.770.70.0
Furniture Assembly BenchmarkMultimodal54.254.20.0
Harvey's Legal Agent Benchmark - Arbitration International Dispute ResolutionLegal0.00.00.0
Harvey's Legal Agent Benchmark - Bankruptcy RestructuringLegal0.00.00.0
Harvey's Legal Agent Benchmark - Emerging Companies Venture CapitalLegal0.00.00.0
Harvey's Legal Agent Benchmark - Employment LaborLegal0.00.00.0
Harvey's Legal Agent Benchmark - Environmental ESGLegal0.00.00.0
Harvey's Legal Agent Benchmark - ImmigrationLegal0.00.00.0
Harvey's Legal Agent Benchmark - InsuranceLegal0.00.00.0
Harvey's Legal Agent Benchmark - International Trade SanctionsLegal0.00.00.0
Harvey's Legal Agent Benchmark - TaxLegal0.00.00.0
Harvey's Legal Agent Benchmark - White Collar Defense InvestigationsLegal0.00.00.0
SciCode (main problems)Science15.815.80.0

GPT-5.6 TerravsMuse Wondernormalised score marginsData Nov 15, 2026Data: Vals AI, Artificial Analysis, Mercor and 23 othersVillage LLM Atlasatlas.village.dev

Win counts use each benchmark’s declared score direction. Represented suite slices and the derived Capability score are excluded from headline totals. Missing or incompatible setups are excluded, never counted as losses.
Loading Atlas data…