Benchmark Almanac

Crest Arcade Nonograms

Gemini 4 Neon 91.7% leads since November 2026
Not in model cards

Models reconstruct a picture from row and column clues in one reply. The score averages the share of exact solutions across six tiers.

Glimmer Index publishes scores for 15 distinct models. Of those, 9 completed the required set.

Made by
Glimmer Index
Kind
Puzzles and chess
Level
Everyday
Scored
Checked automatically
Answers
Short answer
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
15
Entries on its own leaderboard, 14 models we track

Gemini 4 Neon leads with 91.7% Gemini 4 Neon leads with 91.7%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.

  1. 1 Gemini 4 Neon medium · Provisional 91.7%
  2. 2 GPT-6.2 Astra medium 69.4%
  3. 3 GPT-6.1 Sol medium 63.9%
  4. 4 GPT-6 Astra medium 58.3%
  5. 5 Claude Haiku 5.5 medium 58.3%
  6. 6 Claude Sonnet 5.5 medium 47.2%
  7. 7 Gemini 4 Hydrogen medium 47.2%
  8. 8 GPT-6 Sol medium 36.1%
  9. 9 GPT-6.1 Terra medium 27.8%
  10. 10 Qwen3.8-Flash-Next low · Provisional 25%
  11. 11 Qwen 3.8 27B none · Provisional 16.7%
  12. 12 GPT-6 Luna medium 13.9%
  13. 13 Gemma 3 4B none · Provisional 0%
  14. 14 Qwen3.5-9B none · Provisional 0%
  15. 15 Ministral 3 8B none · Provisional 0%

Source: Official Crest Arcade Nonograms leaderboard

#EntryScore ±SettingReleasedRun onSource
1 Gemini 4 Neon 91.7% 73.9 to 100 medium · Provisional Nov 2026 Nov 2026 Official leaderboard
2 GPT-6.2 Astra 69.4% ±10.9 medium Nov 2026 Nov 2026 Official leaderboard
3 GPT-6.1 Sol 63.9% ±10.7 medium Sep 2026 Oct 2026 Official leaderboard
4 GPT-6 Astra 58.3% ±10.3 medium Sep 2026 Oct 2026 Official leaderboard
5 Claude Haiku 5.5 58.3% ±12.1 medium Oct 2026 Nov 2026 Official leaderboard
6 Claude Sonnet 5.5 47.2% ±12.1 medium Sep 2026 Nov 2026 Official leaderboard
7 Gemini 4 Hydrogen 47.2% ±10.7 medium Nov 2026 Nov 2026 Official leaderboard
8 GPT-6 Sol 36.1% ±9.9 medium Sep 2026 Oct 2026 Official leaderboard
9 GPT-6.1 Terra 27.8% ±10.2 medium Oct 2026 Oct 2026 Official leaderboard
10 Qwen3.8-Flash-Next 25% ±14 low · Provisional Aug 2026 Nov 2026 Official leaderboard
11 Qwen 3.8 27B 16.7% 0 to 38.4 none · Provisional Aug 2026 Nov 2026 Official leaderboard
12 GPT-6 Luna 13.9% ±9.9 medium Sep 2026 Oct 2026 Official leaderboard
13 Gemma 3 4B 0% 0 to 21.8 none · Provisional Mar 2025 Nov 2026 Official leaderboard
14 Qwen3.5-9B 0% 0 to 21.8 none · Provisional Feb 2026 Nov 2026 Official leaderboard
15 Ministral 3 8B open weights 0% 0 to 21.8 none · Provisional Nov 2026 Official leaderboard
#ModelScore ±SettingReleasedRun onSource
1 Gemini 4 Neon 91.7% 73.9 to 100 medium · Provisional Nov 2026 Nov 2026 Official leaderboard
2 GPT-6.2 Astra 69.4% ±10.9 medium Nov 2026 Nov 2026 Official leaderboard
3 GPT-6.1 Sol 63.9% ±10.7 medium Sep 2026 Oct 2026 Official leaderboard
4 GPT-6 Astra 58.3% ±10.3 medium Sep 2026 Oct 2026 Official leaderboard
5 Claude Haiku 5.5 58.3% ±12.1 medium Oct 2026 Nov 2026 Official leaderboard
6 Claude Sonnet 5.5 47.2% ±12.1 medium Sep 2026 Nov 2026 Official leaderboard
7 Gemini 4 Hydrogen 47.2% ±10.7 medium Nov 2026 Nov 2026 Official leaderboard
8 GPT-6 Sol 36.1% ±9.9 medium Sep 2026 Oct 2026 Official leaderboard
9 GPT-6.1 Terra 27.8% ±10.2 medium Oct 2026 Oct 2026 Official leaderboard
10 Qwen3.8-Flash-Next 25% ±14 low · Provisional Aug 2026 Nov 2026 Official leaderboard
11 Qwen 3.8 27B 16.7% 0 to 38.4 none · Provisional Aug 2026 Nov 2026 Official leaderboard
12 GPT-6 Luna 13.9% ±9.9 medium Sep 2026 Oct 2026 Official leaderboard
13 Gemma 3 4B 0% 0 to 21.8 none · Provisional Mar 2025 Nov 2026 Official leaderboard
14 Qwen3.5-9B 0% 0 to 21.8 none · Provisional Feb 2026 Nov 2026 Official leaderboard

Rankings by part

We read 6 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as 5 by 5, 10 by 10 and 15 by 15. Gemini 4 Neon leads 3 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.

5 by 5

14 models we track have a score here.

  1. 1 Qwen 3.8 27B ↑10 100%
  2. 2 Qwen3.8-Flash-Next ↑8 100%
  3. 3 GPT-6 Astra ↑1 100%
  4. 4 GPT-6 Sol ↑4 100%
  5. 5 Claude Sonnet 5.5 ↑1 100%
  6. 6 GPT-6.1 Sol ↓3 100%
  7. 7 Claude Haiku 5.5 ↓2 100%
  8. 8 GPT-6.1 Terra ↑1 100%
  9. 9 Gemini 4 Hydrogen ↓2 100%
  10. 10 GPT-6.2 Astra ↓8 100%

The best score, 91.7%, costs $0.61 a task

Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI Anthropic Google DeepMind Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Gemini 4 Neon, medium · Provisional GPT-6.2 Astra, medium GPT-6.1 Sol, medium Claude Haiku 5.5, medium GPT-6.1 Terra, medium GPT-6 Luna, medium 0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Gemini 4 Neon, medium · Provisional GPT-6.2 Astra, medium

Source: Official Crest Arcade Nonograms leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 4 Neon medium · Provisional 91.7% $0.61 40,424
GPT-6.2 Astra medium 69.4% $0.25 4,408
GPT-6.1 Sol medium 63.9% $0.11 9,700
GPT-6 Astra medium 58.3% $0.26 3,676
Claude Haiku 5.5 medium 58.3% $0.04 80,666
Claude Sonnet 5.5 medium 47.2% $0.27 25,863
Gemini 4 Hydrogen medium 47.2% $0.54 71,281
GPT-6 Sol medium 36.1% $0.09 7,275
GPT-6.1 Terra medium 27.8% $0.02 1,434
Qwen3.8-Flash-Next low · Provisional 25% 68,020
Qwen 3.8 27B none · Provisional 16.7% 6,505
GPT-6 Luna medium 13.9% $0.002 1,229
Gemma 3 4B none · Provisional 0% 1,198
Qwen3.5-9B none · Provisional 0% 2,558

The best score, 91.7%, costs $0.61 a task

Runs on the cost frontier score higher than any run that's cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI Anthropic Google DeepMind Cost frontier One model at each effort level
0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Gemini 4 Neon, medium · Provisional GPT-6.2 Astra, medium GPT-6.1 Sol, medium Claude Haiku 5.5, medium GPT-6.1 Terra, medium GPT-6 Luna, medium 0% 20% 40% 60% 80% 100% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale Gemini 4 Neon, medium · Provisional GPT-6.2 Astra, medium

Source: Official Crest Arcade Nonograms leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
Gemini 4 Neon medium · Provisional 91.7% $0.61 40,424
GPT-6.2 Astra medium 69.4% $0.25 4,408
GPT-6.1 Sol medium 63.9% $0.11 9,700
GPT-6 Astra medium 58.3% $0.26 3,676
Claude Haiku 5.5 medium 58.3% $0.04 80,666
Claude Sonnet 5.5 medium 47.2% $0.27 25,863
Gemini 4 Hydrogen medium 47.2% $0.54 71,281
GPT-6 Sol medium 36.1% $0.09 7,275
GPT-6.1 Terra medium 27.8% $0.02 1,434
Qwen3.8-Flash-Next low · Provisional 25% 68,020
Qwen 3.8 27B none · Provisional 16.7% 6,505
GPT-6 Luna medium 13.9% $0.002 1,229
Gemma 3 4B none · Provisional 0% 1,198
Qwen3.5-9B none · Provisional 0% 2,558

7 models have held number one on the official leaderboard since 2023

Lab claims count from the day the card came out, independent runs from the model’s release.

Google DeepMind Qwen OpenAI
Own leaderboard Passed 85% in Nov 2026, by Gemini 4 Neon

Source: Official Crest Arcade Nonograms leaderboard

Gemini 4 Neon on the official leaderboard passed 85% in November 2026

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard Best so far
0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) Gemini 4 Neon GPT-6.2 Astra GPT-6.1 Sol GPT-6 Astra Qwen3.8-Flash-Next Qwen 3.8 27B Gemma 3 4B 0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) Gemini 4 Neon GPT-6.2 Astra

Source: Official Crest Arcade Nonograms 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 Games and long tasks

All 261 in Games and long tasks
  • ARC-AGI-3 In use Interactive game environments where agents must explore, infer goals and rules, and act efficiently without instructions. GPT-6.2 Astra 100%
  • Orak Fading LLM agents play 12 popular video games across most genres through an MCP interface. Each game scores in-game progress or outcomes, and the board ranks models by their average rank across the games. Gemini 2.5 Pro 3.90
  • MineDojo Fading Agents complete open-ended tasks in Minecraft, such as mining blocks and fighting mobs, from a large simulation suite. Programmatic checks score many tasks. Seed2.0 Pro 49%
  • TextQuests Only in system cards Agents play 25 classic interactive fiction games. The score is harmful actions per 100 steps, where lower is better. The board also reports game progress. Llama 4 Scout 7.00
  • GameWorld Only in system cards Multimodal game agents play 34 browser games across 170 tasks. Outcomes are checked from the game state. GPT-6.1 Terra 76.8%
  • Swarm Bench Only in system cards Models orchestrate agent swarms on complex tasks that benefit from coordinated decomposition and parallel execution. Kimi K3 76.3%

Data audit

All 10 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (15 entries).
  • Pass Models scored 14 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from November 2026, for Gemini 4 Neon.
  • Pass Frontier models 5 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Note Headroom Saturated. The best is 91.7%, past 85% since November 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on glimmerindex.com: 14 rows for models we track and 1 other entry 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.

How we check