NoveltyBench
Models give several answers to the same open-ended request. The benchmark measures how many distinct responses they produce and how useful those responses are.
- Made by
- Yiming Zhang and colleagues
- Released
- April 2025
- Kind
- Creative writing
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-6 Astra #4 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
novamine-ai + Claude Opus 5 tops the leaderboard with 6.65 Claude Fable 5.1 leads with 5.32 among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Every run is in the next chart. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. The best model on its own is Claude Fable 5.1, at 5.32. Agents built around a model, such as novamine-ai + Claude Opus 5, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- Claude Opus 5.5
- and 11 more
- 6.65 novamine-ai + Claude Opus 5
- 6.25 novamine-ai-trill + Claude Fable 5
- 5.32 Claude Fable 5.1
- 4.94 Claude Opus 5
- 4.45 GPT-6 Astra
- 4.28 GPT-5.6 Sol
- 4.05 GPT-5.6 Terra
- 3.70 GPT-5.6 Luna
- 2.18 CrPO-llama-3.1-8b-instruct
- 2.00
Gemma 2 27B
- 1.99
Gemma 2 9B
- 1.94 gemini-1.5-pro (snapshot unspecified)
- 1.87
Llama 3.1-405B
- 1.84 Claude 3 Opus
- 1.82 Claude 3.5 Sonnet (October 2024)
- 1.82 GPT-4o
- 1.81 GPT-4o mini
- 1.81
Llama 3.1-8B
- 1.78
Gemini 2.0 Flash
- 1.76
Gemma 2 2B IT
- 1.76
Gemini 2.0 Flash-Lite
- 1.71 c4ai-command-r-08-2024
- 1.71
Command R+
- 1.69
Llama 3.3 70B Instruct
- 1.68 Claude 3.5 Haiku
- 1.65 Llama-3.2-3B-Instruct
- 1.63
Command R7B
- 1.62
Gemini 2.0 Pro
- 1.55
Gemma 3 4B
- 1.50
Gemma 3 27B
- 1.48 Llama-3.2-1B-Instruct
- 1.46
Gemma 3 12B
- 1.23
Gemma 3 1B
- 1 novamine-ai + Claude Opus 5 regenerate, judge v1.1 6.65
- 2 novamine-ai-trill + Claude Fable 5 regenerate, judge v1.1 6.25
- 3 Claude Fable 5.1 in-context, judge v1.1 5.32
- 4 Claude Opus 5 in-context, judge v1.1 4.94
- 5 GPT-6 Astra in-context, judge v1.1 4.45
- 6 GPT-5.6 Sol in-context, judge v1.1 4.28
- 7 GPT-5.6 Terra in-context, judge v1.1 4.05
- 8 GPT-5.6 Luna in-context, judge v1.1 3.70
- 9 CrPO-llama-3.1-8b-instruct regenerate, judge v1.1 2.18
- 10
Gemma 2 27B regenerate, judge v1.1 2.00
- 11
Gemma 2 9B regenerate, judge v1.1 1.99
- 12 gemini-1.5-pro (snapshot unspecified) regenerate, judge v1.1 1.94
- 13
Llama 3.1-405B regenerate, judge v1.1 1.87
- 14 Claude 3 Opus regenerate, judge v1.1 1.84
- 15 Claude 3.5 Sonnet (October 2024) regenerate, judge v1.1 1.82
- 16 GPT-4o Nov 2024, regenerate, judge v1.1 1.82
- 17 GPT-4o mini regenerate, judge v1.1 1.81
- 18
Llama 3.1-8B regenerate, judge v1.1 1.81
- 19
Gemini 2.0 Flash Feb 2025, regenerate, judge v1.1 1.78
- 20
Gemma 2 2B IT regenerate, judge v1.1 1.76
- 21
Gemini 2.0 Flash-Lite regenerate, judge v1.1 1.76
- 22 c4ai-command-r-08-2024 regenerate, judge v1.1 1.71
- 23
Command R+ regenerate, judge v1.1 1.71
- 24
Llama 3.3 70B Instruct regenerate, judge v1.1 1.69
- 25 Claude 3.5 Haiku regenerate, judge v1.1 1.68
- 26 Llama-3.2-3B-Instruct regenerate, judge v1.1 1.65
- 27
Command R7B regenerate, judge v1.1 1.63
- 28
Gemini 2.0 Pro regenerate, judge v1.1 1.62
- 29
Gemma 3 4B regenerate, judge v1.1 1.55
- 30
Gemma 3 27B regenerate, judge v1.1 1.50
- 31 Llama-3.2-1B-Instruct regenerate, judge v1.1 1.48
- 32
Gemma 3 12B regenerate, judge v1.1 1.46
- 33
Gemma 3 1B regenerate, judge v1.1 1.23
Source: Official NoveltyBench leaderboard
- 5.32 Claude Fable 5.1
- 4.94 Claude Opus 5
- 4.45 GPT-6 Astra
- 4.28 GPT-5.6 Sol
- 4.05 GPT-5.6 Terra
- 3.70 GPT-5.6 Luna
- 2.00
Gemma 2 27B
- 1.99
Gemma 2 9B
- 1.87
Llama 3.1-405B
- 1.84 Claude 3 Opus
- 1.82 Claude 3.5 Sonnet (October 2024)
- 1.82 GPT-4o
- 1.81 GPT-4o mini
- 1.81
Llama 3.1-8B
- 1.78
Gemini 2.0 Flash
- 1.76
Gemma 2 2B IT
- 1.76
Gemini 2.0 Flash-Lite
- 1.71 c4ai-command-r-08-2024
- 1.71
Command R+
- 1.69
Llama 3.3 70B Instruct
- 1.68 Claude 3.5 Haiku
- 1.63
Command R7B
- 1.62
Gemini 2.0 Pro
- 1.55
Gemma 3 4B
- 1.50
Gemma 3 27B
- 1.46
Gemma 3 12B
- 1.23
Gemma 3 1B
- 1 Claude Fable 5.1 in-context, judge v1.1 5.32
- 2 Claude Opus 5 in-context, judge v1.1 4.94
- 3 GPT-6 Astra in-context, judge v1.1 4.45
- 4 GPT-5.6 Sol in-context, judge v1.1 4.28
- 5 GPT-5.6 Terra in-context, judge v1.1 4.05
- 6 GPT-5.6 Luna in-context, judge v1.1 3.70
- 7
Gemma 2 27B regenerate, judge v1.1 2.00
- 8
Gemma 2 9B regenerate, judge v1.1 1.99
- 9
Llama 3.1-405B regenerate, judge v1.1 1.87
- 10 Claude 3 Opus regenerate, judge v1.1 1.84
- 11 Claude 3.5 Sonnet (October 2024) regenerate, judge v1.1 1.82
- 12 GPT-4o Nov 2024, regenerate, judge v1.1 1.82
- 13 GPT-4o mini regenerate, judge v1.1 1.81
- 14
Llama 3.1-8B regenerate, judge v1.1 1.81
- 15
Gemini 2.0 Flash Feb 2025, regenerate, judge v1.1 1.78
- 16
Gemma 2 2B IT regenerate, judge v1.1 1.76
- 17
Gemini 2.0 Flash-Lite regenerate, judge v1.1 1.76
- 18 c4ai-command-r-08-2024 regenerate, judge v1.1 1.71
- 19
Command R+ regenerate, judge v1.1 1.71
- 20
Llama 3.3 70B Instruct regenerate, judge v1.1 1.69
- 21 Claude 3.5 Haiku regenerate, judge v1.1 1.68
- 22
Command R7B regenerate, judge v1.1 1.63
- 23
Gemini 2.0 Pro regenerate, judge v1.1 1.62
- 24
Gemma 3 4B regenerate, judge v1.1 1.55
- 25
Gemma 3 27B regenerate, judge v1.1 1.50
- 26
Gemma 3 12B regenerate, judge v1.1 1.46
- 27
Gemma 3 1B regenerate, judge v1.1 1.23
Source: Official NoveltyBench leaderboard
| # | Entry | Score | Setting | Submitted by | Released | Run on | Source |
|---|---|---|---|---|---|---|---|
| 1 | novamine-ai + Claude Opus 5 | 6.65 | regenerate, judge v1.1 | Novamine-AI | Jul 2026 | Aug 2026 | Official leaderboard |
| 2 | novamine-ai-trill + Claude Fable 5 | 6.25 | regenerate, judge v1.1 | Novamine-AI | Jun 2026 | Aug 2026 | Official leaderboard |
| 3 | Claude Fable 5.1 | 5.32 | in-context, judge v1.1 | Sep 2026 | Sep 2026 | Official leaderboard | |
| 4 | Claude Opus 5 | 4.94 | in-context, judge v1.1 | Jul 2026 | Sep 2026 | Official leaderboard | |
| 5 | GPT-6 Astra | 4.45 | in-context, judge v1.1 | Sep 2026 | Sep 2026 | Official leaderboard | |
| 6 | GPT-5.6 Sol | 4.28 | in-context, judge v1.1 | Jul 2026 | Sep 2026 | Official leaderboard | |
| 7 | GPT-5.6 Terra | 4.05 | in-context, judge v1.1 | Jul 2026 | Sep 2026 | Official leaderboard | |
| 8 | GPT-5.6 Luna | 3.70 | in-context, judge v1.1 | Jul 2026 | Sep 2026 | Official leaderboard | |
| 9 | CrPO-llama-3.1-8b-instruct open weights | 2.18 | regenerate, judge v1.1 | mismayil | Nov 2025 | Official leaderboard | |
| 10 | | 2.00 | regenerate, judge v1.1 | Jun 2024 | Mar 2025 | Official leaderboard | |
| 11 | | 1.99 | regenerate, judge v1.1 | Jun 2024 | Mar 2025 | Official leaderboard | |
| 12 | gemini-1.5-pro (snapshot unspecified) closed weights | 1.94 | regenerate, judge v1.1 | Mar 2025 | Official leaderboard | ||
| 13 | | 1.87 | regenerate, judge v1.1 | Jul 2024 | Mar 2025 | Official leaderboard | |
| 14 | Claude 3 Opus | 1.84 | regenerate, judge v1.1 | Feb 2024 | Mar 2025 | Official leaderboard | |
| 15 | Claude 3.5 Sonnet (October 2024) | 1.82 | regenerate, judge v1.1 | Oct 2024 | Mar 2025 | Official leaderboard | |
| 16 | GPT-4o Nov 2024 | 1.82 | regenerate, judge v1.1 | Nov 2024 | Mar 2025 | Official leaderboard | |
| 17 | GPT-4o mini | 1.81 | regenerate, judge v1.1 | Jul 2024 | Mar 2025 | Official leaderboard | |
| 18 | | 1.81 | regenerate, judge v1.1 | Jul 2024 | Mar 2025 | Official leaderboard | |
| 19 | | 1.78 | regenerate, judge v1.1 | Feb 2025 | Mar 2025 | Official leaderboard | |
| 20 | | 1.76 | regenerate, judge v1.1 | Jul 2024 | Mar 2025 | Official leaderboard | |
| 21 | | 1.76 | regenerate, judge v1.1 | Feb 2025 | Mar 2025 | Official leaderboard | |
| 22 | c4ai-command-r-08-2024 | 1.71 | regenerate, judge v1.1 | Aug 2024 | Mar 2025 | Official leaderboard | |
| 23 | | 1.71 | regenerate, judge v1.1 | Aug 2024 | Mar 2025 | Official leaderboard | |
| 24 | | 1.69 | regenerate, judge v1.1 | Dec 2024 | Mar 2025 | Official leaderboard | |
| 25 | Claude 3.5 Haiku | 1.68 | regenerate, judge v1.1 | Oct 2024 | Mar 2025 | Official leaderboard | |
| 26 | Llama-3.2-3B-Instruct open weights | 1.65 | regenerate, judge v1.1 | Mar 2025 | Official leaderboard | ||
| 27 | | 1.63 | regenerate, judge v1.1 | Dec 2024 | Mar 2025 | Official leaderboard | |
| 28 | | 1.62 | regenerate, judge v1.1 | Feb 2025 | Mar 2025 | Official leaderboard | |
| 29 | | 1.55 | regenerate, judge v1.1 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 30 | | 1.50 | regenerate, judge v1.1 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 31 | Llama-3.2-1B-Instruct open weights | 1.48 | regenerate, judge v1.1 | Mar 2025 | Official leaderboard | ||
| 32 | | 1.46 | regenerate, judge v1.1 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 33 | | 1.23 | regenerate, judge v1.1 | Mar 2025 | Sep 2025 | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Released | Run on | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 5.32 | in-context, judge v1.1 | Sep 2026 | Sep 2026 | Official leaderboard | |
| 2 | Claude Opus 5 | 4.94 | in-context, judge v1.1 | Jul 2026 | Sep 2026 | Official leaderboard | |
| 3 | GPT-6 Astra | 4.45 | in-context, judge v1.1 | Sep 2026 | Sep 2026 | Official leaderboard | |
| 4 | GPT-5.6 Sol | 4.28 | in-context, judge v1.1 | Jul 2026 | Sep 2026 | Official leaderboard | |
| 5 | GPT-5.6 Terra | 4.05 | in-context, judge v1.1 | Jul 2026 | Sep 2026 | Official leaderboard | |
| 6 | GPT-5.6 Luna | 3.70 | in-context, judge v1.1 | Jul 2026 | Sep 2026 | Official leaderboard | |
| 7 | | 2.00 | regenerate, judge v1.1 | Jun 2024 | Mar 2025 | Official leaderboard | |
| 8 | | 1.99 | regenerate, judge v1.1 | Jun 2024 | Mar 2025 | Official leaderboard | |
| 9 | | 1.87 | regenerate, judge v1.1 | Jul 2024 | Mar 2025 | Official leaderboard | |
| 10 | Claude 3 Opus | 1.84 | regenerate, judge v1.1 | Feb 2024 | Mar 2025 | Official leaderboard | |
| 11 | Claude 3.5 Sonnet (October 2024) | 1.82 | regenerate, judge v1.1 | Oct 2024 | Mar 2025 | Official leaderboard | |
| 12 | GPT-4o Nov 2024 | 1.82 | regenerate, judge v1.1 | Nov 2024 | Mar 2025 | Official leaderboard | |
| 13 | GPT-4o mini | 1.81 | regenerate, judge v1.1 | Jul 2024 | Mar 2025 | Official leaderboard | |
| 14 | | 1.81 | regenerate, judge v1.1 | Jul 2024 | Mar 2025 | Official leaderboard | |
| 15 | | 1.78 | regenerate, judge v1.1 | Feb 2025 | Mar 2025 | Official leaderboard | |
| 16 | | 1.76 | regenerate, judge v1.1 | Jul 2024 | Mar 2025 | Official leaderboard | |
| 17 | | 1.76 | regenerate, judge v1.1 | Feb 2025 | Mar 2025 | Official leaderboard | |
| 18 | c4ai-command-r-08-2024 | 1.71 | regenerate, judge v1.1 | Aug 2024 | Mar 2025 | Official leaderboard | |
| 19 | | 1.71 | regenerate, judge v1.1 | Aug 2024 | Mar 2025 | Official leaderboard | |
| 20 | | 1.69 | regenerate, judge v1.1 | Dec 2024 | Mar 2025 | Official leaderboard | |
| 21 | Claude 3.5 Haiku | 1.68 | regenerate, judge v1.1 | Oct 2024 | Mar 2025 | Official leaderboard | |
| 22 | | 1.63 | regenerate, judge v1.1 | Dec 2024 | Mar 2025 | Official leaderboard | |
| 23 | | 1.62 | regenerate, judge v1.1 | Feb 2025 | Mar 2025 | Official leaderboard | |
| 24 | | 1.55 | regenerate, judge v1.1 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 25 | | 1.50 | regenerate, judge v1.1 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 26 | | 1.46 | regenerate, judge v1.1 | Mar 2025 | Sep 2025 | Official leaderboard | |
| 27 | | 1.23 | regenerate, judge v1.1 | Mar 2025 | Sep 2025 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official NoveltyBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| novamine-ai + Claude Opus 5 | regenerate, judge v1.1 | novamine-ai | 6.65 | ||
| novamine-ai-trill + Claude Fable 5 | regenerate, judge v1.1 | novamine-ai-trill | 6.25 | ||
| Claude Fable 5.1 | in-context, judge v1.1 | 5.32 | |||
| Claude Opus 5 | in-context, judge v1.1 | 4.94 | |||
| GPT-6 Astra | in-context, judge v1.1 | 4.45 | |||
| GPT-5.6 Sol | in-context, judge v1.1 | 4.28 | |||
| GPT-5.6 Terra | in-context, judge v1.1 | 4.05 | |||
| GPT-5.6 Luna | in-context, judge v1.1 | 3.70 | |||
| Claude Opus 5 | regenerate, judge v1.1 | 2.90 | |||
| Claude Fable 5.1 | regenerate, judge v1.1 | 2.85 | |||
| GPT-6 Astra | regenerate, judge v1.1 | 2.67 | |||
| GPT-5.6 Sol | regenerate, judge v1.1 | 2.62 | |||
| GPT-5.6 Terra | regenerate, judge v1.1 | 2.62 | |||
| GPT-5.6 Luna | regenerate, judge v1.1 | 2.53 | |||
| regenerate, judge v1.1 | 2.00 | ||||
| regenerate, judge v1.1 | 1.99 | ||||
| regenerate, judge v1.1 | 1.87 | ||||
| Claude 3 Opus | regenerate, judge v1.1 | 1.84 | |||
| Claude 3.5 Sonnet (October 2024) | regenerate, judge v1.1 | 1.82 | |||
| GPT-4o Nov 2024 | regenerate, judge v1.1 | 1.82 | |||
| GPT-4o mini | regenerate, judge v1.1 | 1.81 | |||
| regenerate, judge v1.1 | 1.81 | ||||
| regenerate, judge v1.1 | 1.78 | ||||
| regenerate, judge v1.1 | 1.76 | ||||
| regenerate, judge v1.1 | 1.76 | ||||
| c4ai-command-r-08-2024 | regenerate, judge v1.1 | 1.71 | |||
| regenerate, judge v1.1 | 1.71 | ||||
| regenerate, judge v1.1 | 1.69 | ||||
| Claude 3.5 Haiku | regenerate, judge v1.1 | 1.68 | |||
| regenerate, judge v1.1 | 1.63 | ||||
| regenerate, judge v1.1 | 1.62 | ||||
| regenerate, judge v1.1 | 1.55 | ||||
| regenerate, judge v1.1 | 1.50 | ||||
| regenerate, judge v1.1 | 1.46 | ||||
| regenerate, judge v1.1 | 1.23 |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: Official NoveltyBench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.1 | in-context, judge v1.1 | 5.32 | |||
| Claude Opus 5 | in-context, judge v1.1 | 4.94 | |||
| GPT-6 Astra | in-context, judge v1.1 | 4.45 | |||
| GPT-5.6 Sol | in-context, judge v1.1 | 4.28 | |||
| GPT-5.6 Terra | in-context, judge v1.1 | 4.05 | |||
| GPT-5.6 Luna | in-context, judge v1.1 | 3.70 | |||
| Claude Opus 5 | regenerate, judge v1.1 | 2.90 | |||
| Claude Fable 5.1 | regenerate, judge v1.1 | 2.85 | |||
| GPT-6 Astra | regenerate, judge v1.1 | 2.67 | |||
| GPT-5.6 Sol | regenerate, judge v1.1 | 2.62 | |||
| GPT-5.6 Terra | regenerate, judge v1.1 | 2.62 | |||
| GPT-5.6 Luna | regenerate, judge v1.1 | 2.53 | |||
| regenerate, judge v1.1 | 2.00 | ||||
| regenerate, judge v1.1 | 1.99 | ||||
| regenerate, judge v1.1 | 1.87 | ||||
| Claude 3 Opus | regenerate, judge v1.1 | 1.84 | |||
| Claude 3.5 Sonnet (October 2024) | regenerate, judge v1.1 | 1.82 | |||
| GPT-4o Nov 2024 | regenerate, judge v1.1 | 1.82 | |||
| GPT-4o mini | regenerate, judge v1.1 | 1.81 | |||
| regenerate, judge v1.1 | 1.81 | ||||
| regenerate, judge v1.1 | 1.78 | ||||
| regenerate, judge v1.1 | 1.76 | ||||
| regenerate, judge v1.1 | 1.76 | ||||
| c4ai-command-r-08-2024 | regenerate, judge v1.1 | 1.71 | |||
| regenerate, judge v1.1 | 1.71 | ||||
| regenerate, judge v1.1 | 1.69 | ||||
| Claude 3.5 Haiku | regenerate, judge v1.1 | 1.68 | |||
| regenerate, judge v1.1 | 1.63 | ||||
| regenerate, judge v1.1 | 1.62 | ||||
| regenerate, judge v1.1 | 1.55 | ||||
| regenerate, judge v1.1 | 1.50 | ||||
| regenerate, judge v1.1 | 1.46 | ||||
| regenerate, judge v1.1 | 1.23 |
4 models have held number one on the official leaderboard since its release in April 2025
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official NoveltyBench leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official NoveltyBench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Writing and taste
- Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
- WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
- Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing.
MiniMax-Text-01 81.3%
- DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate.
DeepSeek-V4-Pro 62.6%
- Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
- Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right.
Muse Spark 0.21
Data audit
All 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (33 entries).
- Pass Models scored 27 models we track, plus 6 other entries on its leaderboard.
- Pass Newest score The newest is from September 2026, for GPT-6 Astra.
- Note Frontier models Only 2 of the top 10 have a score. The strongest tested is GPT-6 Astra (#4).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on novelty-bench.github.io: 35 rows for models we track and 4 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.