Rotom Champ Bench
Models draft six level 50 Pokémon, select three for each match, and choose their moves. The organizer rates them on wins under Champions singles rules.
The c5 table dated October 21st, 2026 rates 34 language models across 1,506 games. The game count includes other entrants.
- Made by
- The RotomArena Team
- Released
- October 2026
- Kind
- Multi-agent games
- Level
- Competition
- Scored
- Ranked by matches
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Multi-agent
- Environment
- Pokémon Champions
- Items from
- Live play or votes
- Refresh
- Live
- Run by
- A host
- In views
- Games, Agents, Kept fresh
- Strongest model tested
- Claude Opus 5.5 #5 on the capability index
- Last model added
- October 2026
- Scores refreshed
- November 20th, 2026
Gemini 4 Argon leads with 2,304 Gemini 4 Argon leads with 2,304
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.
- 2,304
Gemini 4 Argon
- 2,047
Gemini 3.8 Flash
- 2,003 GPT-6.1 Sol
- 1,954
Muse Wonder
- 1,819 MiMo-V2.6 Flash
- 1,790
DeepSeek V4.1 Flash
- 1,784 GPT-6 Luna Decisions
- 1,783
Gemma 4 31B IT
- 1,778
Muse Spark Open
- 1,754
Muse Spark 1.3
- 1,752 Claude Opus 5.5
- 1,731
DeepSeek-V4-Pro
- 1,731 Grok 4.7
- 1,729 GPT-6 Luna
- 1,728 Claude Haiku 5.5
- 1,709 Claude Sonnet 5.5
- 1,664
Solar Pro 4
- 1,660 Kimi K3
- 1,658 Mercury Decide
- 1,658 GLM-5.3-Flash
- 1,641 GLM-5.3
- 1,629 MiMo-V2.6 Pro
- 1,626
MiniMax-M3
- 1,584 Bonsai 2 27B
- 1,581
Qwen3.8 Flash
- 1,553
Qwen 3.8 27B
- 1,531 Beam 1.0
- 1,528
Qwen 3.8 Max
- 1,512 Jev 1.13
- 1,510
Ling-3.1-flash
- 1,504
MiniMax-M3.1-Flash
- 1,500 gpt-oss-20b
- 1,484
Nemotron 3.5 Super VL
- 1,466 Perplexity Decider V1.2
- 1,458 Microsoft-Decision-1
- 1,435 Ornith 1.5 35B
- 1,379 Drex v2.0
- 1,370 Clef
- 1,325 Ling 3.0 Tiny
- 1,297 Drex v1.5
- 1,291
MiniCPM5-2B
- 1,006 Laya
- 862 Solar Decide Flash
Bars start at 500.
- 1
Gemini 4 Argon 2,304
- 2
Gemini 3.8 Flash 2,047
- 3 GPT-6.1 Sol 2,003
- 4
Muse Wonder 1,954
- 5 MiMo-V2.6 Flash 1,819
- 6
DeepSeek V4.1 Flash 1,790
- 7 GPT-6 Luna Decisions 1,784
- 8
Gemma 4 31B IT 1,783
- 9
Muse Spark Open 1,778
- 10
Muse Spark 1.3 1,754
- 11 Claude Opus 5.5 1,752
- 12
DeepSeek-V4-Pro 1,731
- 13 Grok 4.7 1,731
- 14 GPT-6 Luna 1,729
- 15 Claude Haiku 5.5 1,728
- 16 Claude Sonnet 5.5 1,709
- 17
Solar Pro 4 1,664
- 18 Kimi K3 1,660
- 19 Mercury Decide 1,658
- 20 GLM-5.3-Flash 1,658
- 21 GLM-5.3 1,641
- 22 MiMo-V2.6 Pro 1,629
- 23
MiniMax-M3 1,626
- 24 Bonsai 2 27B 1,584
- 25
Qwen3.8 Flash 1,581
- 26
Qwen 3.8 27B 1,553
- 27 Beam 1.0 1,531
- 28
Qwen 3.8 Max prime 1,528
- 29 Jev 1.13 1,512
- 30
Ling-3.1-flash 1,510
- 31
MiniMax-M3.1-Flash 1,504
- 32 gpt-oss-20b 1,500
- 33
Nemotron 3.5 Super VL 1,484
- 34 Perplexity Decider V1.2 1,466
- 35 Microsoft-Decision-1 1,458
- 36 Ornith 1.5 35B 1,435
- 37 Drex v2.0 1,379
- 38 Clef 1,370
- 39 Ling 3.0 Tiny 1,325
- 40 Drex v1.5 1,297
- 41
MiniCPM5-2B 1,291
- 42 Laya 1,006
- 43 Solar Decide Flash 862
Source: Official Rotom Champ Bench leaderboard
- 2,304
Gemini 4 Argon
- 2,047
Gemini 3.8 Flash
- 2,003 GPT-6.1 Sol
- 1,954
Muse Wonder
- 1,819 MiMo-V2.6 Flash
- 1,790
DeepSeek V4.1 Flash
- 1,783
Gemma 4 31B IT
- 1,778
Muse Spark Open
- 1,754
Muse Spark 1.3
- 1,752 Claude Opus 5.5
- 1,731
DeepSeek-V4-Pro
- 1,731 Grok 4.7
- 1,729 GPT-6 Luna
- 1,728 Claude Haiku 5.5
- 1,709 Claude Sonnet 5.5
- 1,664
Solar Pro 4
- 1,660 Kimi K3
- 1,658 GLM-5.3-Flash
- 1,641 GLM-5.3
- 1,629 MiMo-V2.6 Pro
- 1,626
MiniMax-M3
- 1,581
Qwen3.8 Flash
- 1,553
Qwen 3.8 27B
- 1,531 Beam 1.0
- 1,528
Qwen 3.8 Max
- 1,510
Ling-3.1-flash
- 1,504
MiniMax-M3.1-Flash
- 1,500 gpt-oss-20b
- 1,484
Nemotron 3.5 Super VL
- 1,291
MiniCPM5-2B
Bars start at 1,250.
- 1
Gemini 4 Argon 2,304
- 2
Gemini 3.8 Flash 2,047
- 3 GPT-6.1 Sol 2,003
- 4
Muse Wonder 1,954
- 5 MiMo-V2.6 Flash 1,819
- 6
DeepSeek V4.1 Flash 1,790
- 7
Gemma 4 31B IT 1,783
- 8
Muse Spark Open 1,778
- 9
Muse Spark 1.3 1,754
- 10 Claude Opus 5.5 1,752
- 11
DeepSeek-V4-Pro 1,731
- 12 Grok 4.7 1,731
- 13 GPT-6 Luna 1,729
- 14 Claude Haiku 5.5 1,728
- 15 Claude Sonnet 5.5 1,709
- 16
Solar Pro 4 1,664
- 17 Kimi K3 1,660
- 18 GLM-5.3-Flash 1,658
- 19 GLM-5.3 1,641
- 20 MiMo-V2.6 Pro 1,629
- 21
MiniMax-M3 1,626
- 22
Qwen3.8 Flash 1,581
- 23
Qwen 3.8 27B 1,553
- 24 Beam 1.0 1,531
- 25
Qwen 3.8 Max prime 1,528
- 26
Ling-3.1-flash 1,510
- 27
MiniMax-M3.1-Flash 1,504
- 28 gpt-oss-20b 1,500
- 29
Nemotron 3.5 Super VL 1,484
- 30
MiniCPM5-2B 1,291
Source: Official Rotom Champ Bench leaderboard
| # | Entry | Score ± | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 2,304 2038 to 2619 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 2 | | 2,047 1843 to 2228 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 3 | GPT-6.1 Sol | 2,003 1791 to 2178 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 4 | | 1,954 1651 to 2203 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 5 | MiMo-V2.6 Flash | 1,819 1703 to 1944 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 6 | | 1,790 1663 to 1945 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 7 | GPT-6 Luna Decisions closed weights | 1,784 1675 to 1913 | rotomarena.org | Official leaderboard | ||
| 8 | | 1,783 ±117.5 | Apr 2026 | rotomarena.org | Official leaderboard | |
| 9 | | 1,778 1614 to 1930 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 10 | | 1,754 1641 to 1874 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 11 | Claude Opus 5.5 | 1,752 1609 to 1905 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 12 | | 1,731 1457 to 2086 | Apr 2026 | rotomarena.org | Official leaderboard | |
| 13 | Grok 4.7 | 1,731 1481 to 2088 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 14 | GPT-6 Luna | 1,729 1623 to 1849 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 15 | Claude Haiku 5.5 | 1,728 1624 to 1846 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 16 | Claude Sonnet 5.5 | 1,709 1557 to 1868 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 17 | | 1,664 1540 to 1798 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 18 | Kimi K3 | 1,660 ±192 | Jul 2026 | rotomarena.org | Official leaderboard | |
| 19 | Mercury Decide closed weights | 1,658 1560 to 1764 | rotomarena.org | Official leaderboard | ||
| 20 | GLM-5.3-Flash | 1,658 1556 to 1769 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 21 | GLM-5.3 | 1,641 1498 to 1805 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 22 | MiMo-V2.6 Pro | 1,629 ±153.5 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 23 | | 1,626 1384 to 1889 | Jun 2026 | rotomarena.org | Official leaderboard | |
| 24 | Bonsai 2 27B open weights | 1,584 1492 to 1698 | rotomarena.org | Official leaderboard | ||
| 25 | | 1,581 1485 to 1697 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 26 | | 1,553 1412 to 1700 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 27 | Beam 1.0 | 1,531 1373 to 1740 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 28 | | 1,528 1298 to 1812 | prime | Aug 2026 | rotomarena.org | Official leaderboard |
| 29 | Jev 1.13 closed weights | 1,512 1406 to 1636 | rotomarena.org | Official leaderboard | ||
| 30 | | 1,510 1225 to 1810 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 31 | | 1,504 1396 to 1628 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 32 | gpt-oss-20b | 1,500 | Aug 2025 | rotomarena.org | Official leaderboard | |
| 33 | | 1,484 1380 to 1602 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 34 | Perplexity Decider V1.2 closed weights | 1,466 1355 to 1585 | rotomarena.org | Official leaderboard | ||
| 35 | Microsoft-Decision-1 closed weights | 1,458 1353 to 1571 | rotomarena.org | Official leaderboard | ||
| 36 | Ornith 1.5 35B open weights | 1,435 1334 to 1550 | rotomarena.org | Official leaderboard | ||
| 37 | Drex v2.0 open weights | 1,379 1279 to 1499 | rotomarena.org | Official leaderboard | ||
| 38 | Clef open weights | 1,370 1264 to 1492 | rotomarena.org | Official leaderboard | ||
| 39 | Ling 3.0 Tiny open weights | 1,325 ±119 | rotomarena.org | Official leaderboard | ||
| 40 | Drex v1.5 open weights | 1,297 1178 to 1422 | rotomarena.org | Official leaderboard | ||
| 41 | | 1,291 ±119 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 42 | Laya open weights | 1,006 823 to 1173 | rotomarena.org | Official leaderboard | ||
| 43 | Solar Decide Flash closed weights | 862 549 to 1055 | rotomarena.org | Official leaderboard |
| # | Model | Score ± | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | | 2,304 2038 to 2619 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 2 | | 2,047 1843 to 2228 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 3 | GPT-6.1 Sol | 2,003 1791 to 2178 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 4 | | 1,954 1651 to 2203 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 5 | MiMo-V2.6 Flash | 1,819 1703 to 1944 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 6 | | 1,790 1663 to 1945 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 7 | | 1,783 ±117.5 | Apr 2026 | rotomarena.org | Official leaderboard | |
| 8 | | 1,778 1614 to 1930 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 9 | | 1,754 1641 to 1874 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 10 | Claude Opus 5.5 | 1,752 1609 to 1905 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 11 | | 1,731 1457 to 2086 | Apr 2026 | rotomarena.org | Official leaderboard | |
| 12 | Grok 4.7 | 1,731 1481 to 2088 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 13 | GPT-6 Luna | 1,729 1623 to 1849 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 14 | Claude Haiku 5.5 | 1,728 1624 to 1846 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 15 | Claude Sonnet 5.5 | 1,709 1557 to 1868 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 16 | | 1,664 1540 to 1798 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 17 | Kimi K3 | 1,660 ±192 | Jul 2026 | rotomarena.org | Official leaderboard | |
| 18 | GLM-5.3-Flash | 1,658 1556 to 1769 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 19 | GLM-5.3 | 1,641 1498 to 1805 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 20 | MiMo-V2.6 Pro | 1,629 ±153.5 | Sep 2026 | rotomarena.org | Official leaderboard | |
| 21 | | 1,626 1384 to 1889 | Jun 2026 | rotomarena.org | Official leaderboard | |
| 22 | | 1,581 1485 to 1697 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 23 | | 1,553 1412 to 1700 | Aug 2026 | rotomarena.org | Official leaderboard | |
| 24 | Beam 1.0 | 1,531 1373 to 1740 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 25 | | 1,528 1298 to 1812 | prime | Aug 2026 | rotomarena.org | Official leaderboard |
| 26 | | 1,510 1225 to 1810 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 27 | | 1,504 1396 to 1628 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 28 | gpt-oss-20b | 1,500 | Aug 2025 | rotomarena.org | Official leaderboard | |
| 29 | | 1,484 1380 to 1602 | Oct 2026 | rotomarena.org | Official leaderboard | |
| 30 | | 1,291 ±119 | Sep 2026 | rotomarena.org | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Wins, Losses and Win rate. MiMo-V2.6 Flash leads 1 of them, and 4 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Wins
30 models we track have a score here.
- 1 MiMo-V2.6 Flash ↑4 71.0
- 2
Muse Spark 1.3 ↑7 68.0
- 3 Claude Haiku 5.5 ↑11 67.0
- 4
Gemma 4 31B IT ↑3 66.0
- 5 GPT-6 Luna ↑8 66.0
- 6 GLM-5.3-Flash ↑12 62.0
- 7 gpt-oss-20b ↑21 54.0
- 8
Qwen3.8 Flash ↑14 49.0
- 9
DeepSeek V4.1 Flash ↓3 46.0
- 10
Solar Pro 4 ↑6 38.0
Losses
30 models we track have a score here.
- 1 gpt-oss-20b ↑27 86.0
- 2
MiniCPM5-2B ↑28 62.0
- 3
Nemotron 3.5 Super VL ↑26 42.0
- 4
MiniMax-M3.1-Flash ↑23 38.0
- 5 GLM-5.3-Flash ↑13 37.0
- 6
Qwen3.8 Flash ↑16 35.0
- 7 Claude Haiku 5.5 ↑7 29.0
- 8 GPT-6 Luna ↑5 27.0
- 9
Muse Spark 1.3 25.0
- 10
Gemma 4 31B IT ↓3 24.0
Win rate
30 models we track have a score here.
- 1
Gemini 4 Argon 92.6%
- 2
DeepSeek-V4-Pro ↑9 77.8%
- 3 Grok 4.7 ↑9 77.8%
- 4
DeepSeek V4.1 Flash ↑2 76.7%
- 5 MiMo-V2.6 Flash 76.3%
- 6
Gemma 4 31B IT ↑1 73.3%
- 7
Muse Spark 1.3 ↑2 73.1%
- 8 GPT-6 Luna ↑5 71%
- 9
Gemini 3.8 Flash ↓7 70%
- 10 Claude Haiku 5.5 ↑4 69.8%
Hallucination rate
30 models we track have a score here.
- 1
DeepSeek-V4-Pro ↑10 0%
- 2 Kimi K3 ↑15 0%
- 3
Qwen 3.8 Max ↑22 0%
- 4 GLM-5.3 ↑15 0%
- 5
Qwen 3.8 27B ↑18 0%
- 6
Qwen3.8 Flash ↑16 0%
- 7 Grok 4.7 ↑5 0%
- 8 Claude Opus 5.5 ↑2 0%
- 9 GPT-6 Luna ↑4 0%
- 10 Claude Sonnet 5.5 ↑5 0%
Tokens per turn
30 models we track have a score here.
- 1
Ling-3.1-flash ↑25 9210.0
- 2
MiniMax-M3 ↑19 6037.0
- 3 Grok 4.7 ↑9 3783.0
- 4
Nemotron 3.5 Super VL ↑25 3387.0
- 5
DeepSeek-V4-Pro ↑6 2797.0
- 6
Gemini 4 Argon ↓5 1943.0
- 7
Solar Pro 4 ↑9 1781.0
- 8
Qwen3.8 Flash ↑14 1775.0
- 9
Muse Spark 1.3 1625.0
- 10
MiniCPM5-2B ↑20 1617.0
The best score, 2,304, costs $0.24 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.
Source: Official Rotom Champ Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| 2,304 | $0.24 | ||||
| 2,047 | $0.03 | ||||
| GPT-6.1 Sol | 2,003 | $0.09 | |||
| 1,954 | $0.26 | ||||
| MiMo-V2.6 Flash | 1,819 | $0.005 | |||
| 1,790 | $0.01 | ||||
| 1,783 | $0.005 | ||||
| 1,778 | $0.07 | ||||
| 1,754 | $0.007 | ||||
| Claude Opus 5.5 | 1,752 | $0.27 | |||
| 1,731 | $0.11 | ||||
| Grok 4.7 | 1,731 | $0.30 | |||
| GPT-6 Luna | 1,729 | $0.005 | |||
| Claude Haiku 5.5 | 1,728 | $0.008 | |||
| Claude Sonnet 5.5 | 1,709 | $0.08 | |||
| 1,664 | $0.009 | ||||
| Kimi K3 | 1,660 | $0.07 | |||
| GPT-6 Luna | pro | 1,660 | $0.02 | ||
| GLM-5.3-Flash | 1,658 | $0.003 | |||
| GLM-5.3 | 1,641 | $0.01 | |||
| MiMo-V2.6 Pro | 1,629 | $0.02 | |||
| 1,626 | $0.11 | ||||
| 1,581 | $0.01 | ||||
| 1,553 | $0.03 | ||||
| Beam 1.0 | 1,531 | $0.03 | |||
| prime | 1,528 | $0.25 | |||
| 1,510 | $0.03 | ||||
| 1,504 | |||||
| gpt-oss-20b | 1,500 | ||||
| 1,484 | |||||
| 1,291 |
The best score, 2,304, costs $0.24 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.
Source: Official Rotom Champ Bench leaderboard
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| 2,304 | $0.24 | ||||
| 2,047 | $0.03 | ||||
| GPT-6.1 Sol | 2,003 | $0.09 | |||
| 1,954 | $0.26 | ||||
| MiMo-V2.6 Flash | 1,819 | $0.005 | |||
| 1,790 | $0.01 | ||||
| 1,783 | $0.005 | ||||
| 1,778 | $0.07 | ||||
| 1,754 | $0.007 | ||||
| Claude Opus 5.5 | 1,752 | $0.27 | |||
| 1,731 | $0.11 | ||||
| Grok 4.7 | 1,731 | $0.30 | |||
| GPT-6 Luna | 1,729 | $0.005 | |||
| Claude Haiku 5.5 | 1,728 | $0.008 | |||
| Claude Sonnet 5.5 | 1,709 | $0.08 | |||
| 1,664 | $0.009 | ||||
| Kimi K3 | 1,660 | $0.07 | |||
| GPT-6 Luna | pro | 1,660 | $0.02 | ||
| GLM-5.3-Flash | 1,658 | $0.003 | |||
| GLM-5.3 | 1,641 | $0.01 | |||
| MiMo-V2.6 Pro | 1,629 | $0.02 | |||
| 1,626 | $0.11 | ||||
| 1,581 | $0.01 | ||||
| 1,553 | $0.03 | ||||
| Beam 1.0 | 1,531 | $0.03 | |||
| prime | 1,528 | $0.25 | |||
| 1,510 | $0.03 | ||||
| 1,504 | |||||
| gpt-oss-20b | 1,500 | ||||
| 1,484 | |||||
| 1,291 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official Rotom Champ Bench 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 Rotom Champ Bench 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
- 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 (43 entries).
- Pass Models scored 30 models we track, plus 13 other entries on its leaderboard.
- Pass Newest score The newest is from October 2026, for MiniMax-M3.1-Flash.
- Pass Frontier models 4 of the top 10 have a score, led by Claude Opus 5.5 (#5).
- Note Headroom Scored as an Elo rating, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on rotomarena.org: 31 rows for models we track and 13 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.