Benchmark Almanac

Crest Arcade Elemental Armory

GPT-6.1 Terra 67.3% leads since October 2026
Not in model cards

Models equip four elemental balls with cards, then select and aim a ball each round. The score averages match win rates across three levels.

Glimmer Index publishes scores for 18 distinct models. Of those, 9 completed the required set.

Made by
Glimmer Index
Kind
Video games
Level
Everyday
Scored
Checked automatically
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Multi-agent
Environment
Elemental Armory
Items from
Live play or votes
Refresh
One fixed set
Run by
Anyone
In views
Games, Agents
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
18
Entries on its own leaderboard, 17 models we track

GPT-6.1 Terra leads with 67.3% GPT-6.1 Terra leads with 67.3%

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 GPT-6.1 Terra medium 67.3%
  2. 2 Gemini 4 Carbon medium · Provisional 66.7%
  3. 3 GPT-6.2 Astra medium 58.7%
  4. 4 GPT-6 Astra medium 53.3%
  5. 5 Claude Haiku 5.5 medium 52.7%
  6. 6 GPT-6 Sol medium 52%
  7. 7 GPT-6 Luna medium 51.3%
  8. 8 Gemini 4 Neon medium · Provisional 50%
  9. 9 GPT-6.1 Sol medium 48.7%
  10. 10 Claude Sonnet 5.5 medium 48%
  11. 11 Gemini 4 Hydrogen medium 48%
  12. 12 Qwen3.8-Flash-Next low · Provisional 41.7%
  13. 13 Gemma 3 4B none · Provisional 33.3%
  14. 14 gpt-oss-20b low · Provisional 33.3%
  15. 15 Qwen3.5-9B none · Provisional 33.3%
  16. 16 Qwen 3.8 27B none · Provisional 33.3%
  17. 17 Gemini 4 Argon medium · Provisional 33.3%
  18. 18 Ministral 3 8B none · Provisional 16.7%

Source: Official Crest Arcade Elemental Armory leaderboard

#EntryScore ±SettingReleasedRun onSource
1 GPT-6.1 Terra 67.3% ±7.4 medium Oct 2026 Oct 2026 Official leaderboard
2 Gemini 4 Carbon 66.7% ±30.8 medium · Provisional Oct 2026 Nov 2026 Official leaderboard
3 GPT-6.2 Astra 58.7% ±7.8 medium Nov 2026 Nov 2026 Official leaderboard
4 GPT-6 Astra 53.3% ±7.8 medium Sep 2026 Oct 2026 Official leaderboard
5 Claude Haiku 5.5 52.7% ±7.6 medium Oct 2026 Nov 2026 Official leaderboard
6 GPT-6 Sol 52% ±7.8 medium Sep 2026 Oct 2026 Official leaderboard
7 GPT-6 Luna 51.3% ±7.9 medium Sep 2026 Oct 2026 Official leaderboard
8 Gemini 4 Neon 50% ±25.8 medium · Provisional Nov 2026 Nov 2026 Official leaderboard
9 GPT-6.1 Sol 48.7% ±7.8 medium Sep 2026 Oct 2026 Official leaderboard
10 Claude Sonnet 5.5 48% ±7.8 medium Sep 2026 Nov 2026 Official leaderboard
11 Gemini 4 Hydrogen 48% ±7.8 medium Nov 2026 Nov 2026 Official leaderboard
12 Qwen3.8-Flash-Next 41.7% ±22.7 low · Provisional Aug 2026 Nov 2026 Official leaderboard
13 Gemma 3 4B 33.3% ±30.8 none · Provisional Mar 2025 Oct 2026 Official leaderboard
14 gpt-oss-20b 33.3% ±30.8 low · Provisional Aug 2025 Oct 2026 Official leaderboard
15 Qwen3.5-9B 33.3% ±27.1 none · Provisional Feb 2026 Nov 2026 Official leaderboard
16 Qwen 3.8 27B 33.3% ±27.1 none · Provisional Aug 2026 Nov 2026 Official leaderboard
17 Gemini 4 Argon 33.3% ±30.8 medium · Provisional Sep 2026 Nov 2026 Official leaderboard
18 Ministral 3 8B open weights 16.7% 0 to 42.5 none · Provisional Nov 2026 Official leaderboard
#ModelScore ±SettingReleasedRun onSource
1 GPT-6.1 Terra 67.3% ±7.4 medium Oct 2026 Oct 2026 Official leaderboard
2 Gemini 4 Carbon 66.7% ±30.8 medium · Provisional Oct 2026 Nov 2026 Official leaderboard
3 GPT-6.2 Astra 58.7% ±7.8 medium Nov 2026 Nov 2026 Official leaderboard
4 GPT-6 Astra 53.3% ±7.8 medium Sep 2026 Oct 2026 Official leaderboard
5 Claude Haiku 5.5 52.7% ±7.6 medium Oct 2026 Nov 2026 Official leaderboard
6 GPT-6 Sol 52% ±7.8 medium Sep 2026 Oct 2026 Official leaderboard
7 GPT-6 Luna 51.3% ±7.9 medium Sep 2026 Oct 2026 Official leaderboard
8 Gemini 4 Neon 50% ±25.8 medium · Provisional Nov 2026 Nov 2026 Official leaderboard
9 GPT-6.1 Sol 48.7% ±7.8 medium Sep 2026 Oct 2026 Official leaderboard
10 Claude Sonnet 5.5 48% ±7.8 medium Sep 2026 Nov 2026 Official leaderboard
11 Gemini 4 Hydrogen 48% ±7.8 medium Nov 2026 Nov 2026 Official leaderboard
12 Qwen3.8-Flash-Next 41.7% ±22.7 low · Provisional Aug 2026 Nov 2026 Official leaderboard
13 Gemma 3 4B 33.3% ±30.8 none · Provisional Mar 2025 Oct 2026 Official leaderboard
14 gpt-oss-20b 33.3% ±30.8 low · Provisional Aug 2025 Oct 2026 Official leaderboard
15 Qwen3.5-9B 33.3% ±27.1 none · Provisional Feb 2026 Nov 2026 Official leaderboard
16 Qwen 3.8 27B 33.3% ±27.1 none · Provisional Aug 2026 Nov 2026 Official leaderboard
17 Gemini 4 Argon 33.3% ±30.8 medium · Provisional Sep 2026 Nov 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Level 1, Level 5 and Level 8. Each ranks models on one part of the test. Gemini 4 Argon leads 1 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.

Level 1

17 models we track have a score here.

  1. 1 Gemini 4 Argon ↑16 100%
  2. 2 Gemini 4 Carbon 100%
  3. 3 GPT-6.1 Terra ↓2 74%
  4. 4 Claude Haiku 5.5 ↑1 72%
  5. 5 GPT-6.2 Astra ↓2 62%
  6. 6 Gemini 4 Hydrogen ↑5 56%
  7. 7 GPT-6 Sol ↓1 54%
  8. 8 GPT-6.1 Sol ↑1 54%
  9. 9 Qwen 3.8 27B ↑7 50%
  10. 10 Qwen3.8-Flash-Next ↑2 50%

The best score, 67.3%, costs $0.01 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 Cost frontier One model at each effort level
0% 20% 40% 60% 80% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale GPT-6.1 Terra, medium Claude Haiku 5.5, medium 0% 20% 40% 60% 80% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale GPT-6.1 Terra, medium Claude Haiku 5.5, medium

Source: Official Crest Arcade Elemental Armory leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6.1 Terra medium 67.3% $0.01
Gemini 4 Carbon medium · Provisional 66.7% $0.21
GPT-6.2 Astra medium 58.7% $0.12
GPT-6 Astra medium 53.3% $0.17
Claude Haiku 5.5 medium 52.7% $0.004
GPT-6 Sol medium 52% $0.05
GPT-6 Luna medium 51.3% $0.002
Gemini 4 Neon medium · Provisional 50% $0.15
GPT-6.1 Sol medium 48.7% $0.04
Claude Sonnet 5.5 medium 48% $0.04
Gemini 4 Hydrogen medium 48% $0.08
Qwen3.8-Flash-Next low · Provisional 41.7%
Gemma 3 4B none · Provisional 33.3%
gpt-oss-20b low · Provisional 33.3%
Qwen3.5-9B none · Provisional 33.3%
Qwen 3.8 27B none · Provisional 33.3%
Gemini 4 Argon medium · Provisional 33.3% $0.03

The best score, 67.3%, costs $0.01 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 Cost frontier One model at each effort level
0% 20% 40% 60% 80% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale GPT-6.1 Terra, medium Claude Haiku 5.5, medium 0% 20% 40% 60% 80% $0.001 $0.01 $0.10 $1.00 Cost per task, log scale GPT-6.1 Terra, medium Claude Haiku 5.5, medium

Source: Official Crest Arcade Elemental Armory leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6.1 Terra medium 67.3% $0.01
Gemini 4 Carbon medium · Provisional 66.7% $0.21
GPT-6.2 Astra medium 58.7% $0.12
GPT-6 Astra medium 53.3% $0.17
Claude Haiku 5.5 medium 52.7% $0.004
GPT-6 Sol medium 52% $0.05
GPT-6 Luna medium 51.3% $0.002
Gemini 4 Neon medium · Provisional 50% $0.15
GPT-6.1 Sol medium 48.7% $0.04
Claude Sonnet 5.5 medium 48% $0.04
Gemini 4 Hydrogen medium 48% $0.08
Qwen3.8-Flash-Next low · Provisional 41.7%
Gemma 3 4B none · Provisional 33.3%
gpt-oss-20b low · Provisional 33.3%
Qwen3.5-9B none · Provisional 33.3%
Qwen 3.8 27B none · Provisional 33.3%
Gemini 4 Argon medium · Provisional 33.3% $0.03

4 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 4 leaders

Source: Official Crest Arcade Elemental Armory leaderboard

Scores over time

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%) GPT-6.1 Terra GPT-6 Astra Qwen3.8-Flash-Next Gemma 3 4B 0% 20% 40% 60% 80% 100% 2025 2026 2027 Near the ceiling (85%) GPT-6.1 Terra GPT-6 Astra

Source: Official Crest Arcade Elemental Armory 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 11 checks pass. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 5 pass
  • Pass Independent runs Scores from the official leaderboard (18 entries).
  • Pass Models scored 17 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 7 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Pass Headroom The best is 67.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on glimmerindex.com: 17 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