GPT-6.1 Terra ranks #23 of 87 models on the November 2026 ToneBench board through its best configuration, GPT-6.1 Terra (max). This setting, GPT-6.1 Terra (xhigh), is #53 of 151 configurations, with a Writing Score of 80.1/100 and a Writing Elo of 1860. One script costs $0.028 at API list price.
Last updated , from board data generated at 17:52 UTC.
Rank, scores, the nine metrics, the 10 reference scripts, cost and setup for one
configuration (a model at one reasoning setting). Key Results sums it up; the section links below it jump to the detail.
Model Rank ?
#23 of 87 modelsthrough GPT-6.1 Terra (max); this setting is #53 of 151 configurations
Writing Score ?
80.1 out of 100
Writing Elo ?
1860 95% range 1819 to 1898
Cost per Script
$0.028 at API list price
Key Results
StandingGPT-6.1 Terra ranks #23 of 87 models through its best configuration, GPT-6.1 Terra (max). This setting is #53 of 151 configurations by Writing Elo (1860), in the middle third of the board. Its 95% range (1819 to 1898) overlaps 23 other configurations, ranked #38 to #61.
MetricsBest-ranked: Slop Score (87.8, 22nd of 151 configurations, +6.5 against the board median). Lowest-ranked: YouTube Best Practices (76.5, 73rd of 151 configurations, +0.2 against the board median).
ScriptsFrom 78.2 on Script 4 (short explainer) to 83.9 on Script 9 (career guide): a 5.7-point spread across the 10 reference scripts.
ConsistencyIts Writing Score moves ± 1.9 between drafts of the same script, against ± 2.5 for the median configuration: typical.
ValueMiMo-V2.6-Flash (thinking on) ranks higher with an overlapping Elo range and costs about $0.0057 per script, against $0.028 per script for this one.
Louis's PickI'd use GPT-6.1 Terra (high) instead: same model, a higher rank with an overlapping Elo range for less per script.
More Context Behind These Results
Writing Elo comes from comparing its average on each script with every other configuration's average on that same script; a gap smaller than the draft-to-draft variation counts as a draw (what the ranges can and cannot show).
On Slop Score, its best-ranked metric, its drafts carry fewer filler phrases and AI tells to clean out. Even its lowest-ranked metric, YouTube Best Practices, ranks in the top half of the board, so no metric stands out as a weak spot.
The script format moves its score. If most of your scripts look like its best or weakest format, that result is a better guide than the average.
It outranks 48 configurations that cost at least 50% more.
Among proprietary models, GPT-6.1 Terra is 17th of 53. This setting is 43rd of 108 proprietary configurations. The best open-weight configuration, GLM-5.3 (max) at configuration #22, outranks it.
Lab
OpenAI 6th of 13 modelsthis setting 17th of 32 configurations
Weights
Proprietary 17th of 53 modelsthis setting 43rd of 108 configurations
Consistency
± 1.9 typical spread
Average Tokens
16.1k input + output
Time per Script
0.5 min average, retries included
Highest-Ranked in This LabGPT-6 Sol (max) ranks highest of the OpenAI configurations by Writing Elo, with a Writing Score +3.4 against this configuration, for about 10 cents more per script.
GPT-6.1 Terra is also on the board at other effort settings, and GPT-6.1 Terra (max) ranks higher, though their Elo ranges overlap. The thinking-level page for GPT-6.1 Terra charts how quality, cost and time change with the setting.
Each corner is one metric on a 0 to 100 scale; the further out, the higher the score. A corner outside the dashed line beats the board median. Hover or tap a point for its exact score, and a metric name for what it rewards.
GPT-6.1 Terra (xhigh)Board medianBoard best per metricMax possible (100)
Scores by Metric
Nine metrics, each scored 0 to 100 and weighted into the Writing Score; the weight sits under each name. Rank is out of all 151 ranked configurations.
Score colors:Strong: 82 and upMiddle: 65 to 81.9Weak: under 65
This modelBoard best (upper line)Board median (lower line)±: spread between drafts?: what the metric rewards
Tone & Voice Match ?19% weight · +1.2 vs median
board best 82.8 · Claude Opus 5.5 (max effort)75.2± 1.5 · 72ndboard median 74.0
Writing Craft & Clarity ?13% weight · +3.6 vs median
board best 83.2 · Claude Opus 5.5 (xhigh)78.6± 1.0 · 29thboard median 75.0
Substance, Accuracy & Value ?15% weight · +3.8 vs median
board best 88.4 · Claude Opus 5.5 (xhigh)85.6± 0.9 · 33rdboard median 81.8
Continuity & Emotion ?14% weight · +1.5 vs median
board best 85.7 · Claude Opus 5.5 (max effort)79.0± 1.2 · 62ndboard median 77.5
YouTube Best Practices ?12% weight · +0.2 vs median
board best 84.5 · Claude Fable 5.2 (max effort)76.5± 2.0 · 73rdboard median 76.4
Hook Strength ?10% weight · +1.2 vs median
board best 84.0 · Claude Fable 5.2 (xhigh)80.8± 2.5 · 54thboard median 79.6
Length Adherence ?8% weight · +2.0 vs median
board best 99.0 · Claude Fable 5.2 (xhigh)86.8± 5.1 · 69thboard median 84.8
Slop Score ?5% weight · +6.5 vs median
board best 89.0 · GPT-6 Sol (medium)87.8± 1.0 · 22ndboard median 81.3
Visual Cue Quality ?4% weight · +3.1 vs median
board best 85.9 · Claude Opus 5.5 (max effort)77.8± 1.8 · 56thboard median 74.8
Scores by Reference Script
Every ranked configuration writes five drafts for each of the same 10 briefs, and each score is the mean of those drafts. The rank and board median compare it with every configuration on that script, which separates a weak result from a hard script. The result on the format closest to your own work is the most relevant.
Script 1
opinion / warning explainer
79.9
out of 100
48th of 151 configurations on this script · board median 77.2
Script 2
news-analysis / skeptical explainer
81.7
out of 100
35th of 151 configurations on this script · board median 78.4
Script 3
personal roadmap / opinion
79.0
out of 100
56th of 151 configurations on this script · board median 77.2
Script 4
short explainer
78.2
out of 100
54th of 151 configurations on this script · board median 75.7
Script 5
news-analysis / opinion explainer
78.4
out of 100
71st of 151 configurations on this script · board median 78.0
Script 6
founder announcement / personal origin story
80.6
out of 100
61st of 151 configurations on this script · board median 79.2
Script 7
personal technical walkthrough / agentic workflow case study
80.3
out of 100
49th of 151 configurations on this script · board median 77.9
Script 8
product release announcement / personal observation
79.8
out of 100
64th of 151 configurations on this script · board median 79.0
Script 9
career guide / hiring analysis
83.9
out of 100
28th of 151 configurations on this script · board median 79.3
Script 10
engineering process walkthrough / presentation adaptation
79.4
out of 100
37th of 151 configurations on this script · board median 75.0
Consistency Between Drafts
Every score on this page is the mean of 5 drafts per script. The ± is the standard deviation between those drafts: the larger it is, the more two drafts of the same script can differ.
Compared with the typical model, it's steadiest on Substance, Accuracy & Value: ± 0.9 between drafts against ± 2.1.
Consistency by Metric
Metric
This model
Board median
Verdict
Tone & Voice Match ?
75.2 ± 1.5
± 1.9
typical
Writing Craft & Clarity ?
78.6 ± 1.0
± 1.5
typical
Substance, Accuracy & Value ?
85.6 ± 0.9
± 2.1
steadier than most
Continuity & Emotion ?
79.0 ± 1.2
± 1.5
typical
YouTube Best Practices ?
76.5 ± 2.0
± 2.4
typical
Hook Strength ?
80.8 ± 2.5
± 2.7
typical
Length Adherence ?
86.8 ± 5.1
± 6.6
typical
Slop Score ?
87.8 ± 1.0
± 1.6
typical
Visual Cue Quality ?
77.8 ± 1.8
± 2.9
typical
Cost, Time and Tokens per Script
Logged on every run; none of these figures affects the Writing Score. Time is the average time to one accepted script, retries included. Cost is one script at the API list price.
Time per Script
0.5 minfaster than the board median of 1.5 min
Prompt tokens in
13.2kstyle guide + brief + research packet
Tokens Out
2.9kscript + any reasoning tokens
Cost per Script
$0.028provider-counted output, thinking included, plus the fixed prompt priced once; varies ± 0.007 between drafts
List Price Used
$1 / $5input / output, per million tokens
Scores by Judge
Four judges score the same 50 stored drafts blind against the same rubric: three LLM judges from three labs, plus Jev, a typed judge from TypeSafe that rates each metric on five described quality levels. No single judge's taste decides the result. The Writing Score of 80.1 combines their scores with the parts computed in code (Length Adherence and half of the Slop Score). The highest and lowest judge are 12.6 points apart on its Writing Score. That is close to the board median of 13.4. Each judge also has its own scale, so every card shows that judge's score against its average across the board. How the panel works.
Claude Opus 5.5 (medium)
Anthropic
74.9
+6.2 against its board average of 68.7
GLM 5.3 Flash
Z.ai
87.4
+4.6 against its board average of 82.9
GPT-6.1 Sol (medium)
OpenAI
82.9
+11.0 against its board average of 71.9
Jev 1.13
TypeSafe
75.3
+1.3 against its board average of 74.0
Evaluation Setup
How this exact configuration was run and judged: route, model ID, dates, sampling and prompt.
Accessed viaCodex CLI (OpenAI subscription) · model page ↗.
Exact model / route idgpt-6.1-terra at reasoning level: xhigh.
Generations5 independent runs × 10 scripts = 50 drafts, stored after generation and never edited.
Run dates2026-10-26.
JudgesClaude Opus 5.5 at medium effort through the Claude Code subscription, GPT-6.1 Sol at medium reasoning through the Codex CLI, GLM 5.3 Flash through OpenRouter, and Jev 1.13 from TypeSafe. One call per judge per draft. All four score every draft on their own, blind to which model wrote it. The three LLM judges use the identical rubric and have to quote evidence before they score a metric. Jev answers the same rubric as one question per metric, choosing among five described quality levels, and writes no text. Seven metrics are the plain average of the four judges. Length is computed from the spoken word count, and Slop is half computed (lexical scans minus the spoken-dash penalty) and half judged. The Writing Elo is cross-checked with a Bradley-Terry fit of the same pairwise results (methodology).
Sampling and promptThe provider's default sampling, with no fine-tuning and no system-prompt changes. Every current-ranked model gets the same prompt, about 13,000 tokens (the count shifts a bit with each model's tokenizer): a style guide built from Louis's voice and storytelling guides, the target length, and the brief with its research packet. Generation is closed-book on every route: the prompt is the only source, with no web search, browsing, code execution, file access or other tool (generation).
What stays privateThe exact rubric and any non-public reference material. Each script is normally benchmarked before its video is published, which lowers the odds that a model has seen the reference, though it does not rule it out (why).
Frequently Asked Questions
How Good Is GPT-6.1 Terra (xhigh) at Writing?
GPT-6.1 Terra ranks #23 of 87 models on ToneBench through its best configuration, GPT-6.1 Terra (max). This configuration is #53 of 151 configurations, in the middle third of the board, with a Writing Elo of 1860 and a Writing Score of 80.1/100. The ranks come from full YouTube scripts written in the voice of Louis-François Bouchard and judged blind, with the channel's finished script as the reference. The benchmark measures long-form scripted writing, so the result does not carry over to every kind of text.
Is GPT-6.1 Terra (xhigh) the Best OpenAI Model for Writing?
No. GPT-6.1 Terra is 6th of 13 OpenAI models. The top one is GPT-6 Sol, through GPT-6 Sol (max), about 441 Elo ahead of this setting.
Is GPT-6.1 Terra (xhigh) Good Value for the Money?
It costs about $0.028 per script. MiMo-V2.6-Flash (thinking on) ranks higher with an overlapping Elo range and costs less.
What Are the Strengths and Weaknesses of GPT-6.1 Terra (xhigh)?
Its best-ranked metric is Slop Score (87.8, 22nd of 151 configurations, +6.5 against the board median), and its lowest-ranked is YouTube Best Practices (76.5, 73rd of 151, +0.2). Even that one ranks in the top half of the board. The Scores by Metric section shows the board median and the board's best for each one.
How Was GPT-6.1 Terra (xhigh) Evaluated?
It was run through the Codex CLI (OpenAI subscription), with the exact model/route ID gpt-6.1-terra at reasoning effort xhigh, first run on 2026-10-26. It wrote each script 5 times with the provider's default sampling and no fine-tuning. The Evaluation Setup section and the methodology page have the details.
Does GPT-6.1 Terra (xhigh) Have Open Weights?
No. It is a proprietary model: its weights are not public. Among proprietary configurations it is 43rd of 108 for writing.