Skip to content
VECTOR WIREAI INTELLIGENCE
⌘K
UTC
Models728Deals30d254Policy30d66, 13 pendingSources985

GPT-6.1 Sol vs GPT-6 Luna

17 SHARED BENCHMARKS

Across 17 shared benchmarks, GPT-6.1 Sol scores higher on 14 and GPT-6 Luna on 1, with 2 level. The widest gap is HealthBench Hard length-adjusted, where GPT-6.1 Sol scores 36.2 against 31.4. GPT-6 Luna is the cheaper of the two on tracked API pricing ($0.10 against $2.00 per million input tokens).

OPENAIVSOPENAI17 SHARED14–1 HEAD-TO-HEADNEWEST SCORE ADDED

At a glance

GPT-6.1 SolGPT-6 Luna
MakerOpenAIOpenAI
Released—
Price per 1M tokens input / output$2.00 / $10.00$0.10 / $0.50
Cost of 1M in + 1M out$12.00$0.60 20.0× less
Head-to-head of 17 shared benchmarks14 wins1 wins
Scores tracked independently verified17 0 ◆121 33 ◆

GPT-6 Luna's release date per Artificial Analysis. Prices: Artificial Analysis for GPT-6.1 Sol; Artificial Analysis for GPT-6 Luna. ◆ = independently verified score.

Every shared benchmark17 · grouped by area

Other shared benchmarks 17

BenchmarkGPT-6.1 SolMARGINGPT-6 Luna
Dynamic Benchmarks - Emotional reliance11
Dynamic Benchmarks - Mental health11
Dynamic Benchmarks - Self-harm10.9
HealthBench Consensus length-adjusted9695.9
HealthBench Hard length-adjusted36.231.4
HealthBench Professional length-adjusted64.260.8
Image input evaluations - extremism11
Image input evaluations - harms-erotic11
Image input evaluations - hate11
Image input evaluations - self-harm11
Production Benchmarks - Gore0.90.9
U18 evaluations - Age-restricted goods, services, and dangerous challenges / activities0.90.8
U18 evaluations - Eating Disorders10.9
U18 evaluations - Emotional Reliance10.9
U18 evaluations - Gore0.90.9
U18 evaluations - Self Harm11
U18 evaluations - Sexual Content10.9

Each score is the one the model's own page shows — the most authoritative tracked result for that benchmark, on the benchmark's standard methodology (source-attributed). ↓ marks lower-is-better metrics; ◆ an independently verified score. Open either model for its full surface, provenance and pricing. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (direct, direct), otherwise the lowest tracked offer.