Undominated.ai

Alternatives to GPT-6 Luna

OpenAI LMArena 1391.5 $0.200/M on a balanced workload prices as of 2026-10-06

Every higher-scoring or cheaper alternative has a recorded capability loss.

Of the 144 models carrying both an independent score and a published price at the same delivery mode, 9 score at least as high as GPT-6 Luna and cost no more under at least one listed workload, with at least one of those dimensions improved. 9 have a recorded capability loss, named on every row.

Dominance is not a property of a model. It is a property of a model, a capability lens and a workload, and all three are named on every row. Scores are LMArena Elo, used under CC BY 4.0 from the official dataset; prices are blended per million tokens. A higher score is not a drop-in replacement.

This page is built only while a candidate improves score or price without worsening the other under a listed workload. When that comparison no longer holds, it is not generated.

Where it holds

WorkloadGPT-6 Luna $/MRecorded capabilities preservedRecorded capability losses
Balanced$0.20007
Summarise$0.09404
Chat$0.23306
Code gen$0.33308
Agentic$0.10606

Workload mixes are defined on the methodology page. Cached input is priced at the cached rate, and reasoning tokens at the worse of the reasoning and output rates.

What you would be replacing

Intelligence1391.5
Context window1M
Max output128K
Input modesfile, image, text
Tool useyes
Extended reasoningyes

Preserving recorded capabilities requires matching or beating these fields. Full record for GPT-6 Luna, or check GPT-6 Luna against the whole catalogue.

Alternatives with recorded capability losses 9

These improve score or price without worsening the other under the listed workloads, but reduce at least one recorded capability. Read the last column before switching.

ModelIntelligence$/MHolds underRecorded capability loss
DeepSeek V4.1 Flash DeepSeek1462.5 +71$0.182
  • Balanced −9%
  • Summarise −29%
  • Agentic −1%
  • 1.1M → 1M context
  • no file input
MiMo-V2.6-Flash Xiaomi1456.4 +64.9$0.175
  • Balanced −13%
  • Chat −34%
  • Code gen −36%
  • Agentic −25%
  • no file input
Gemma 4 26B A4B Google1433.9 +42.4$0.127
  • Balanced −37%
  • Summarise −27%
  • Chat −36%
  • Code gen −39%
  • Agentic −25%
  • 1.1M → 262K context
  • no file input
DeepSeek V4 Flash 0423 DeepSeek1432.1 +40.6$0.113
  • Balanced −44%
  • Summarise −22%
  • Chat −55%
  • Code gen −58%
  • Agentic −43%
  • 1.1M → 1M context
  • no file, image input
MiMo-V2.5 Xiaomi1427.5 +36$0.175
  • Balanced −13%
  • Chat −34%
  • Code gen −36%
  • Agentic −25%
  • no file input
Step 3.5 Flash StepFun1403 +11.5$0.150
  • Balanced −25%
  • Chat −23%
  • Code gen −34%
  • 1.1M → 262K context
  • 128K → 66K max output
  • no file, image input
Qwen3.5-Flash Qwen1397 tie$0.114
  • Balanced −43%
  • Summarise −21%
  • Chat −39%
  • Code gen −45%
  • Agentic −11%
  • 1.1M → 1M context
  • 128K → 66K max output
  • no file input
Gemma 4 31B Google1443.4 +51.9$0.296 code gen
  • Code gen −11%
  • 1.1M → 262K context
  • 128K → 16K max output
  • no file input
DeepSeek V3.2 DeepSeek1424.5 +33$0.322 code gen
  • Code gen −3%
  • 1.1M → 164K context
  • 128K → 66K max output
  • no file, image input

What this compares, and what it leaves out

  • Quality is LMArena Elo, used under CC BY 4.0 from the official dataset. The 95% confidence interval on a difference between two scores is about ±10.47 points, so a gap smaller than that is marked tie rather than an improvement — see significance bands.
  • 204 further models at this delivery mode carry a price but no independent score. They are absent from the comparison in both directions — unrated is not a zero, and an unmeasured model is neither an alternative nor a worse buy.
  • Retired models are never offered as an alternative, and a model only competes against its own delivery mode: batch trades latency for price, so it is not a like-for-like swap.
  • Nothing here measures latency, throughput, rate limits or how a model behaves on your prompts. Two models with the same index score are not interchangeable.
  • Models with no higher-scoring or cheaper alternative that is no worse on the other axis are on the value frontier. Models with such an alternative are listed here.
Evidence & Ask
Markdown for LLMs