Benchmark Almanac

Crest Arcade Hustle Sim

GPT-6.2 Astra 83.7 leads since November 2026
Not in model cards

Models buy upgrades and hire helpers to reach earnings targets in an idle game. The score compares simulated completion times with reference strategies.

Glimmer Index publishes scores for 18 distinct models. Of those, 14 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
Agentic
Environment
Hustle Sim
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-6.2 Astra leads with 83.7 GPT-6.2 Astra leads with 83.7

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 GPT-6.2 Astra medium 83.7
  2. 2 Gemini 4 Hydrogen medium 74.7
  3. 3 Gemini 4 Neon medium 70.1
  4. 4 Claude Sonnet 5.5 medium 64.2
  5. 5 GPT-6 Astra medium 61.6
  6. 6 Gemini 4 Carbon medium · Provisional 59.8
  7. 7 GPT-6 Sol medium 56.0
  8. 8 Claude Haiku 5.5 medium 54.6
  9. 9 GPT-6.1 Terra medium 46.0
  10. 10 GPT-6.1 Sol medium 45.0
  11. 11 GPT-6 Luna medium 36.2
  12. 12 Qwen3.8-Flash-Next low 34.2
  13. 13 Qwen 3.8 27B none 21.3
  14. 14 Gemini 4 Argon medium · Provisional 18.2
  15. 15 gpt-oss-20b low · Provisional 12.4
  16. 16 Ministral 3 8B none 8.9
  17. 17 Gemma 3 4B none · Provisional 6.1
  18. 18 Qwen3.5-9B none 2.6

Source: Official Crest Arcade Hustle Sim leaderboard

#EntryScore ±SettingReleasedRun onSource
1 GPT-6.2 Astra 83.7 ±23.1 medium Nov 2026 Nov 2026 Official leaderboard
2 Gemini 4 Hydrogen 74.7 ±27.4 medium Nov 2026 Nov 2026 Official leaderboard
3 Gemini 4 Neon 70.1 ±25.6 medium Nov 2026 Nov 2026 Official leaderboard
4 Claude Sonnet 5.5 64.2 ±27.7 medium Sep 2026 Nov 2026 Official leaderboard
5 GPT-6 Astra 61.6 ±26.8 medium Sep 2026 Nov 2026 Official leaderboard
6 Gemini 4 Carbon 59.8 ±31.6 medium · Provisional Oct 2026 Nov 2026 Official leaderboard
7 GPT-6 Sol 56.0 ±24.8 medium Sep 2026 Nov 2026 Official leaderboard
8 Claude Haiku 5.5 54.6 ±27.8 medium Oct 2026 Nov 2026 Official leaderboard
9 GPT-6.1 Terra 46.0 ±25.2 medium Oct 2026 Nov 2026 Official leaderboard
10 GPT-6.1 Sol 45.0 ±24.7 medium Sep 2026 Nov 2026 Official leaderboard
11 GPT-6 Luna 36.2 ±27.6 medium Sep 2026 Oct 2026 Official leaderboard
12 Qwen3.8-Flash-Next 34.2 ±27.8 low Aug 2026 Nov 2026 Official leaderboard
13 Qwen 3.8 27B 21.3 0 to 48.1 none Aug 2026 Nov 2026 Official leaderboard
14 Gemini 4 Argon 18.2 0 to 50 medium · Provisional Sep 2026 Nov 2026 Official leaderboard
15 gpt-oss-20b 12.4 0 to 43.9 low · Provisional Aug 2025 Nov 2026 Official leaderboard
16 Ministral 3 8B open weights 8.9 0 to 34.7 none Nov 2026 Official leaderboard
17 Gemma 3 4B 6.1 0 to 37.3 none · Provisional Mar 2025 Oct 2026 Official leaderboard
18 Qwen3.5-9B 2.6 0 to 27.5 none Feb 2026 Nov 2026 Official leaderboard
#ModelScore ±SettingReleasedRun onSource
1 GPT-6.2 Astra 83.7 ±23.1 medium Nov 2026 Nov 2026 Official leaderboard
2 Gemini 4 Hydrogen 74.7 ±27.4 medium Nov 2026 Nov 2026 Official leaderboard
3 Gemini 4 Neon 70.1 ±25.6 medium Nov 2026 Nov 2026 Official leaderboard
4 Claude Sonnet 5.5 64.2 ±27.7 medium Sep 2026 Nov 2026 Official leaderboard
5 GPT-6 Astra 61.6 ±26.8 medium Sep 2026 Nov 2026 Official leaderboard
6 Gemini 4 Carbon 59.8 ±31.6 medium · Provisional Oct 2026 Nov 2026 Official leaderboard
7 GPT-6 Sol 56.0 ±24.8 medium Sep 2026 Nov 2026 Official leaderboard
8 Claude Haiku 5.5 54.6 ±27.8 medium Oct 2026 Nov 2026 Official leaderboard
9 GPT-6.1 Terra 46.0 ±25.2 medium Oct 2026 Nov 2026 Official leaderboard
10 GPT-6.1 Sol 45.0 ±24.7 medium Sep 2026 Nov 2026 Official leaderboard
11 GPT-6 Luna 36.2 ±27.6 medium Sep 2026 Oct 2026 Official leaderboard
12 Qwen3.8-Flash-Next 34.2 ±27.8 low Aug 2026 Nov 2026 Official leaderboard
13 Qwen 3.8 27B 21.3 0 to 48.1 none Aug 2026 Nov 2026 Official leaderboard
14 Gemini 4 Argon 18.2 0 to 50 medium · Provisional Sep 2026 Nov 2026 Official leaderboard
15 gpt-oss-20b 12.4 0 to 43.9 low · Provisional Aug 2025 Nov 2026 Official leaderboard
16 Gemma 3 4B 6.1 0 to 37.3 none · Provisional Mar 2025 Oct 2026 Official leaderboard
17 Qwen3.5-9B 2.6 0 to 27.5 none Feb 2026 Nov 2026 Official leaderboard

Rankings by part

We read 3 parts from the benchmark’s own leaderboard: Fresh start, Takeover and Empire. Each ranks models on one part of the test. Gemini 4 Hydrogen 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.

Fresh start

17 models we track have a score here.

  1. 1 Gemini 4 Hydrogen ↑1 82.5
  2. 2 GPT-6 Sol ↑5 78.6
  3. 3 Claude Sonnet 5.5 ↑1 77.1
  4. 4 GPT-6 Astra ↑1 76.2
  5. 5 GPT-6.1 Sol ↑5 70.3
  6. 6 GPT-6.2 Astra ↓5 70.2
  7. 7 GPT-6 Luna ↑4 59.9
  8. 8 Qwen3.8-Flash-Next ↑4 46.0
  9. 9 Claude Haiku 5.5 ↓1 45.8
  10. 10 GPT-6.1 Terra ↓1 43.8

The best score, 83.7, costs $1.25 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
0.0 20.0 40.0 60.0 80.0 100.0 $0.01 $0.10 $1.00 $10 Cost per task, log scale GPT-6.2 Astra, medium Gemini 4 Hydrogen, medium Claude Sonnet 5.5, medium GPT-6 Sol, medium Claude Haiku 5.5, medium GPT-6 Luna, medium 0.0 20.0 40.0 60.0 80.0 100.0 $0.01 $0.10 $1.00 $10 Cost per task, log scale GPT-6.2 Astra, medium Gemini 4 Hydrogen, medium

Source: Official Crest Arcade Hustle Sim leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6.2 Astra medium 83.7 $1.25
Gemini 4 Hydrogen medium 74.7 $0.76
Gemini 4 Neon medium 70.1 $3.70
Claude Sonnet 5.5 medium 64.2 $0.38
GPT-6 Astra medium 61.6 $1.41
Gemini 4 Carbon medium · Provisional 59.8 $5.01
GPT-6 Sol medium 56.0 $0.30
Claude Haiku 5.5 medium 54.6 $0.03
GPT-6.1 Terra medium 46.0 $0.13
GPT-6.1 Sol medium 45.0 $0.31
GPT-6 Luna medium 36.2 $0.01
Qwen3.8-Flash-Next low 34.2
Qwen 3.8 27B none 21.3
Gemini 4 Argon medium · Provisional 18.2 $0.15
gpt-oss-20b low · Provisional 12.4
Gemma 3 4B none · Provisional 6.1
Qwen3.5-9B none 2.6

The best score, 83.7, costs $1.25 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
0.0 20.0 40.0 60.0 80.0 100.0 $0.01 $0.10 $1.00 $10 Cost per task, log scale GPT-6.2 Astra, medium Gemini 4 Hydrogen, medium Claude Sonnet 5.5, medium GPT-6 Sol, medium Claude Haiku 5.5, medium GPT-6 Luna, medium 0.0 20.0 40.0 60.0 80.0 100.0 $0.01 $0.10 $1.00 $10 Cost per task, log scale GPT-6.2 Astra, medium Gemini 4 Hydrogen, medium

Source: Official Crest Arcade Hustle Sim leaderboard

ModelEffortHarnessScoreCost per taskOutput tokens
GPT-6.2 Astra medium 83.7 $1.25
Gemini 4 Hydrogen medium 74.7 $0.76
Gemini 4 Neon medium 70.1 $3.70
Claude Sonnet 5.5 medium 64.2 $0.38
GPT-6 Astra medium 61.6 $1.41
Gemini 4 Carbon medium · Provisional 59.8 $5.01
GPT-6 Sol medium 56.0 $0.30
Claude Haiku 5.5 medium 54.6 $0.03
GPT-6.1 Terra medium 46.0 $0.13
GPT-6.1 Sol medium 45.0 $0.31
GPT-6 Luna medium 36.2 $0.01
Qwen3.8-Flash-Next low 34.2
Qwen 3.8 27B none 21.3
Gemini 4 Argon medium · Provisional 18.2 $0.15
gpt-oss-20b low · Provisional 12.4
Gemma 3 4B none · Provisional 6.1
Qwen3.5-9B none 2.6

8 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 OpenAI Qwen Anthropic
Own leaderboard 8 leaders

Source: Official Crest Arcade Hustle Sim 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
0 20 40 60 80 100 2025 2026 2027 0 20 40 60 80 100 2025 2026 2027

Source: Official Crest Arcade Hustle Sim 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 (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).
  • Note Headroom Scored as an index, with no fixed ceiling.
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