Atlas

Compare Models

GPT-6.2 Sol vs Muse Ember

GPT-6.2 Sol leads by 4.8 capability points (≈95% interval +2.2 to +7.4): a clear lead over Muse Ember · P(higher) ≈ 100%

Wins 37 of 49 shared benchmarks (11 lost, 1 tied)

Capability vs. relative cost
GPT-6.2 SolMuse EmberClosed weightsOpen weights

Benchmark wins37 – 11 · 49 shared, 1 tied

Comparing matching setups only (8 benchmarks excluded) · suites counted once
← GPT-6.2 SolMuse Ember →
Data: Artificial Analysis, Vals AI, Surge AI and 5 othersatlas.village.dev

Margins

Each benchmark scaled 0–100% (its declared range, else the field’s range); Δ is Muse Ember minus GPT-6.2 Sol.

Terminal-Bench-Science 0.1Science › Multidisciplinary67.620.0−47.6
Humanity's Last Exam DiamondKnowledge & reasoning › General knowledge64.025.1−38.9
Code Migration v1.1 (Vals Index v2.2 subset)Software › Software engineering85.347.1−38.2
TaxCalcBench TY25Professional › Finance, accounting & tax32.02.0−30.0
RiemannBench (November 2026 rescoring)Math80.053.6−26.4
EnterpriseBench: CoreCraftTool & computer use › Customer service & operations36.462.1+25.7
Artificial Analysis Intelligence Index v5.0.1Composite indexes57.336.0−21.2
Terminal-Bench 4.0Software › Software engineering60.639.4−21.2
LMArena Agent Arena Net Improvement (Steering Burden)Tool & computer use › General agents11.31.0−20.2
Artificial Analysis Engineering IndexScience › Engineering61.241.8−19.4
Terminal-Bench 4.0 (Artificial Analysis)Software › Software engineering60.140.9−19.2
Medical Long Context Reasoning (MLCR-AA, October 2026 methodology)Health & medicine37.218.3−18.9
Ramp SWE-Bench v2 (Bash harness)Software › Software engineering72.454.4−18.0
FrontierCode 2.0 (Artificial Analysis)Software › Software engineering44.427.2−17.2
Artificial Analysis Legal IndexProfessional › Legal55.038.5−16.6
Artificial Analysis Economics IndexComposite indexes57.441.0−16.4
AA-Omniscience v1.1 IndexKnowledge & reasoning › General knowledge40.47.7−16.3
CritPt v2 (agentic, avg@5)Science › Physical sciences78.662.3−16.3
LMArena Agent Arena Praise vs ComplaintTool & computer use › General agents23.3-2.7−13.0
HLAB-Vals-1.1Professional › Legal12.125.0+12.9
Artificial Analysis Finance & Accounting IndexProfessional › Finance, accounting & tax57.244.6−12.6
Professional Reasoning Benchmark - LegalProfessional › Legal43.355.6+12.3
Legal Research BenchProfessional › Legal37.049.0+12.0
Artificial Analysis Healthcare & Medical IndexHealth & medicine53.341.3−12.0
Artificial Analysis Strategy & Ops IndexProfessional › General knowledge work59.448.7−10.7
ComplexConstraints (November 2026 rescoring)Language & writing › Instruction following69.558.8−10.7
DrugDiscoveryBenchScience › Life sciences62.252.4−9.8
Vals Legal IndexProfessional › Legal66.775.7+9.0
DAYJOB: Finance (October 2026 rescoring)Professional › Finance, accounting & tax32.824.2−8.6
Tax Agent BenchProfessional › Finance, accounting & tax62.971.4+8.5
Chartography (November 2026 rescoring)Perception & media › Documents & charts87.779.3−8.4
GDP.pdf (Artificial Analysis, All-pass)Professional › General knowledge work30.022.8−7.2
GDP.xlsxProfessional › General knowledge work22.315.4−6.9
LMArena Agent Arena Confirmed SuccessTool & computer use › General agents10.9-2.0−6.5
Vals Index v2.2Composite indexes66.160.5−5.6
AA-Briefcase v1.1 EloProfessional › General knowledge work16121520−5.0
Finance Agent v2.1Professional › Finance, accounting & tax58.963.8+4.9
HANDBOOK.md Agents v1.1Tool & computer use › Customer service & operations34.529.8−4.7
SWE Atlas v1.1 - OverallSoftware › Software engineering60.556.0−4.5
LMArena Agent Arena Steering BurdenTool & computer use › General agents13.44.8−4.3
Vals Finance IndexProfessional › Finance, accounting & tax56.760.9+4.3
Vibe Code Bench v1.1Software › Frontend & design87.683.7−3.9
AutomationBench-AA 1.0.6Tool & computer use › Customer service & operations71.368.1−3.2
SimpleBenchKnowledge & reasoning › General knowledge69.972.7+2.8
Excel Modeling Benchmark v1.1Professional › Finance, accounting & tax74.372.2−2.1
LMArena Agent Arena Bash ReliabilityTool & computer use › General agents4.36.6+1.2
GDP.pdf (November 2026 rescoring)Professional › General knowledge work48.849.2+0.4
LMArena Agent Arena Tool HallucinationTool & computer use › Tool calling1.20.9−0.1
DAYJOB: Healthcare (October 2026 rescoring)Health & medicine17.217.20.0
Data: Artificial Analysis, Vals AI, Surge AI and 5 othersatlas.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…