← comparisons · head to head

GPT-6.1 Terra vs GPT-6 Luna

GPT-6.1 Terra scores higher than GPT-6 Luna on all 3 public leaderboards that rate both. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, GPT-6.1 Terra is at 75 and GPT-6 Luna at 26.9 (out of 100).

Scores as published by each board; table composed October 28, 2026.

Get the next launch alert, free →

Leaderboard by leaderboard

BoardGPT-6.1 TerraGPT-6 LunaHigher
LMArena
Elo (community votes)
1,670.71,579.8GPT-6.1 Terra
Vals AI
Vals Index accuracy % · weighted finance + coding tasks
60.252.3GPT-6.1 Terra
Artificial Analysis
intelligence index · measured runs only
5127.8GPT-6.1 Terra

Raw scores are each board's own scale, so compare within a row, not across rows. Full table: the bench index.

GPT-6.1 Terra at a glance

Developer
OpenAI
Status
Live since October 26, 2026
API price
$1 input / $5 output per 1M tokens · OpenAI, gpt-6.1-terra
Context window
1.05M tokens

Live — Oct 26 · $1 / $5 per MTok, cached input $0.05, cache writes $1.25 (OpenAI's model page) · 1.05M ctx / 128K out · knowledge cutoff Jun 1, 2026 · reasoning, text and image in · GPT-5.6 Terra lists at $2 / $12 on OpenRouter · first seen Oct 16-19 as the judge model in Microsoft's dotnet/efcore eval configs (PR #39217) · our sweep caught gpt-6.1-terra at 17:52 UTC and fired at 17:53 · OpenRouter added openai/gpt-6.1-terra (18:13 UTC) and openai/gpt-6.1-terra-pro (18:15) the same evening, both at $1 / $5 and 1.05M ctx · scored on LMArena, Vals and Artificial Analysis by Oct 28.

GPT-6.1 Terra is live in OpenAI's API at $1 / $5 per million tokens, under GPT-5.6 Terra's $2 / $12

2026-10-26 · OpenAI's GPT-6.1 Terra is live in its API. Our radar saw the gpt-6.1-terra id at 17:52 UTC on October 26 and fired the alert at 17:53, before OpenRouter listed it.

GPT-6.1 Terra turns up again, as a cheaper reviewer in a GitHub engineer's Copilot workflow

2026-10-25 · A second public repo now calls GPT-6.1 Terra, a model OpenAI has not announced. On October 24 at 03:48 UTC, Nate Finch, whose GitHub profile lists his company as GitHub, merged a pull request in his own public repo, natefinch/council4, that moves every review step from gpt-6.1-sol to gpt-6.1-terra at high effort.

Full GPT-6.1 Terra tracker →

GPT-6 Luna at a glance

Developer
OpenAI
Status
Live since September 22, 2026
API price
$0.10 input / $0.50 output per 1M tokens · OpenAI, gpt-6-luna
Context window
1.05M tokens

Live — Sep 22, in the API and ChatGPT (Free and Go too) the same day · the cheap, high-volume tier · models.dev lists gpt-6-luna on OpenAI's own API (read Sep 24).

OpenAI opens the Decisions API: GPT-6 Luna returns probabilities, choices and scores for $0.10 per million input tokens

2026-10-06 · OpenAI has opened a public beta of the Decisions API, a new endpoint (POST /v1/decisions) where the model answers a question about your input with a number or a label instead of writing text. GPT-6 Luna is the only model it runs.

Full GPT-6 Luna tracker →

GPT-6.1 Terra vs GPT-6 Luna: quick answers

Which is better, GPT-6.1 Terra or GPT-6 Luna?

It depends on what you measure. GPT-6.1 Terra scores higher than GPT-6 Luna on all 3 public leaderboards that rate both. GPT-6.1 Terra's widest lead is on Artificial Analysis. On the ArtificialWatch Index, which takes the median of each model's percentile across the boards that score it, GPT-6.1 Terra is at 75 and GPT-6 Luna at 26.9 (out of 100).

Which is newer, GPT-6.1 Terra or GPT-6 Luna?

GPT-6.1 Terra. It went live on October 26, 2026, 34 days after GPT-6 Luna (September 22, 2026).

Which is cheaper, GPT-6.1 Terra or GPT-6 Luna?

GPT-6 Luna is cheaper on both input and output. On each vendor's own API, GPT-6.1 Terra is $1 input / $5 output per million tokens and GPT-6 Luna is $0.10 input / $0.50 output per million tokens. GPT-6.1 Terra's rate rises for prompts over 272K tokens; GPT-6 Luna's rate rises for prompts over 272K tokens. Prices as published in the models.dev catalog, as of 2026-10-27.

Which has the bigger context window, GPT-6.1 Terra or GPT-6 Luna?

Neither. Both take 1.05M tokens.

Who makes GPT-6.1 Terra and GPT-6 Luna?

Both are from OpenAI.

Where do these numbers come from?

Each score is the leaderboard's own published figure, read by ArtificialWatch (table composed October 28, 2026). Boards measure different things, so raw scores are only comparable within a row.

More comparisons

GPT-6 Astra vs Claude Fable 5.1GPT-6 Astra vs GPT-5.6GPT-6 Astra vs Claude Opus 5Claude Fable 5.1 vs Claude Fable 5Claude Fable 5.1 vs Claude Opus 5Claude Opus 5 vs GPT-5.6Claude Opus 5 vs Claude Opus 4.8Claude Opus 5 vs Claude Fable 5Claude Opus 5 vs Kimi K3Kimi K3 vs Claude Fable 5Kimi K3 vs GLM-5.2Kimi K3 vs GPT-5.6DeepSeek V4 Pro vs GLM-5.2DeepSeek V4 Pro vs Kimi K3Grok 4.7 vs GPT-6 AstraGrok 4.7 vs Claude Opus 5Grok 4.7 vs Claude Fable 5.1Qwen 3.8 Max vs Claude Opus 5Qwen 3.8 Max vs Claude Fable 5Qwen 3.8 Max vs Kimi K3Qwen 3.8 Max vs DeepSeek V4 ProQwen 3.8 Max vs GLM-5.2Qwen 3.8 Max vs GPT-5.6GPT-6 Astra vs Claude Fable 5Claude Fable 5 vs Claude Opus 4.8Claude Fable 5 vs Claude Sonnet 5Claude Sonnet 5 vs Claude Opus 4.8Claude Sonnet 5 vs Claude Opus 5GLM-5.2 vs Claude Opus 4.8GLM-5.2 vs Claude Fable 5GLM-5.2 vs GPT-5.5Gemini 3.5 Flash vs Gemini 3.1 ProGemini 3.5 Flash vs Claude Sonnet 5GPT-6 Astra vs Claude Opus 4.8Claude Fable 5.1 vs Claude Opus 4.8Kimi K3 vs Claude Opus 4.8DeepSeek V4 Pro vs Claude Opus 4.8DeepSeek V4 Pro vs GPT-5.5DeepSeek V4 Pro vs Claude Fable 5GLM-5.3 vs Kimi K3GLM-5.3 vs GLM-5.2GLM-5.3 vs GPT-6 AstraGrok 4.6 vs Claude Opus 5Grok 4.6 vs Claude Fable 5Grok 4.6 vs GPT-5.6Grok 4.6 vs Grok 4.5Grok 4.6 vs Claude Sonnet 5Gemini 3.8 Flash vs Gemini 3.1 ProGemini 3.8 Flash vs Claude Opus 5Muse Spark 1.3 vs Gemini 3.8 FlashMuse Spark 1.3 vs GLM-5.3GPT-6 Sol vs GPT-6 AstraGPT-6 Sol vs Claude Opus 5GPT-6 Sol vs Claude Fable 5GPT-6 Luna vs GPT-6 AstraGPT-6 Sol vs GPT-6 LunaClaude Fable 5 vs GPT-5.6Claude Opus 4.8 vs GPT-5.5GPT-5.6 vs Claude Opus 4.8GPT-5.6 vs Claude Sonnet 5Claude Sonnet 5 vs GPT-5.5Claude Fable 5 vs GPT-5.5DeepSeek V4 Pro vs Claude Opus 5Qwen 3.8 Max vs GLM-5.3Qwen 3.8 Max vs Claude Opus 4.8GLM-5.3 Flash vs GLM-5.3GLM-5.3 Flash vs GLM-5.2MiniMax M3 vs Kimi K3MiniMax M3 vs DeepSeek V4 ProMiniMax M3 vs GLM-5.2MiniMax M3 vs GPT-5.5GLM-5.3 vs DeepSeek V4 ProGLM-5.3 vs Claude Opus 5GLM-5.3 vs Claude Fable 5Kimi K3 vs DeepSeek V4.1 FlashGrok 4.7 vs Grok 4.6Muse Spark 1.3 vs Claude Fable 5.1Muse Spark 1.3 vs Claude Opus 5Muse Spark 1.3 vs DeepSeek V4.1 FlashMuse Spark 1.3 vs Grok 4.6Muse Spark 1.3 vs GPT-6 AstraGemini 3.8 Flash vs GPT-6 AstraGemini 3.8 Flash vs Claude Fable 5.1Gemini 3.8 Flash vs Claude Sonnet 5Gemini 3.8 Flash vs Grok 4.6Gemini 3.8 Flash vs GPT-5.6GPT-5.6 vs GPT-5.5Claude Sonnet 5.5 vs Claude Opus 5.5Claude Haiku 5.5 vs Claude Sonnet 5.5Claude Sonnet 5.5 vs Claude Sonnet 5Claude Sonnet 5.5 vs GPT-6.1 SolClaude Sonnet 5.5 vs Claude Opus 5Claude Sonnet 5.5 vs Claude Opus 4.8GPT-6.1 Sol vs GPT-6 AstraGPT-6.1 Sol vs Claude Opus 5.5GPT-6.1 Sol vs GPT-5.6GPT-6.1 Sol vs GPT-6 SolClaude Haiku 5.5 vs GPT-6 LunaClaude Haiku 5.5 vs Claude Opus 5.5Claude Haiku 5.5 vs Claude Sonnet 5Claude Haiku 5.5 vs Gemini 3.8 FlashClaude Opus 5.5 vs Claude Fable 5.1Claude Opus 5.5 vs GPT-6 AstraClaude Opus 5.5 vs Claude Opus 5Mistral Large 4 vs Claude Opus 5.5GPT-6 Luna vs Claude Sonnet 5.5GPT-6 Luna vs GPT-6.1 SolClaude Fable 5.1 vs Claude Sonnet 5.5Gemini 3.8 Flash vs GLM-5.3 FlashMuse Wonder vs Claude Opus 5.5Gemini 4 Argon vs GPT-6 AstraGemini 4 Argon vs Claude Opus 5.5Gemini 4 Argon vs Claude Fable 5.1Kimi K3.1 Pro vs Claude Opus 5.5GPT-6.1 Terra vs GPT-6.1 SolGPT-6.1 Terra vs GPT-6 AstraGPT-6.1 Terra vs Claude Sonnet 5.5GPT-6.1 Terra vs Claude Opus 5.5GPT-6.1 Terra vs Claude Haiku 5.5
sweeping every 60 seconds

Hear when the next one drops. Free.

Free: a Chrome push and an email about 15 minutes after a new model answers on a public API. Members get a text or a phone call the moment a launch is confirmed.

  • Free forever
  • No card
  • Unsubscribe in one click

Want it the minute it answers? Try Signal 7 days free →

Also: the bench index · API pricing · what a workload costs on each · the wire