Benchmark Almanac

Pokémon VGC Bench (Ricotoma)

GPT-6 Astra 1,901 leads since September 2026
Not in model cards

Agents play competitive Pokémon doubles with assigned teams. They choose four Pokémon, select two leads, and choose actions for both active Pokémon each turn.

Ricotoma ranks 16 systems across 108 best-of-three series and 247 battles. Ratings use series winners and account for opponent strength.

Made by
Ricotoma
Kind
Multi-agent games
Level
Competition
Scored
Ranked by matches
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Multi-agent
Environment
Pokémon
Items from
Live play or votes
Refresh
Live
Run by
A host
In views
Games, Agents, Kept fresh
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
16
Entries on its own leaderboard, 14 models we track

GPT-6 Astra leads with 1,901 among models released by September 2026 GPT-6 Astra leads with 1,901 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 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.

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:

Bars start at 800.

  1. 1 GPT-6 Astra high 1,901
  2. 2 GPT-6.1 Sol high 1,847
  3. 3 Gemini 3.8 Flash high 1,744
  4. 4 GPT-6 Sol high 1,641
  5. 5 Claude Fable 5.1 high 1,614
  6. 6 Muse Spark 1.3 high 1,614
  7. 7 Claude Opus 5.5 high 1,614
  8. 8 GPT-5.6 Sol high 1,566
  9. 9 Kimi K3 high 1,482
  10. 10 GLM-5.3 high 1,482
  11. 11 Grok 4.7 high 1,482
  12. 12 GPT-6 Luna high 1,380
  13. 13 GPT-5.6 Terra high 1,276
  14. 14 GPT-5.6 Luna high 1,268
  15. 15 Clef none 1,115
  16. 16 Jev 1.13 none 973

Source: Official Pokémon VGC Bench (Ricotoma) leaderboard

#EntryScore ±SettingDateSource
1 GPT-6 Astra 1,901 ±180.2 high Sep 2026 Official leaderboard
2 GPT-6.1 Sol 1,847 ±235.2 high Sep 2026 Official leaderboard
3 Gemini 3.8 Flash 1,744 ±289.4 high Sep 2026 Official leaderboard
4 GPT-6 Sol 1,641 ±138.3 high Sep 2026 Official leaderboard
5 Claude Fable 5.1 1,614 ±284.3 high Sep 2026 Official leaderboard
6 Muse Spark 1.3 1,614 ±284.3 high Sep 2026 Official leaderboard
7 Claude Opus 5.5 1,614 ±284.3 high Sep 2026 Official leaderboard
8 GPT-5.6 Sol 1,566 ±243 high Jul 2026 Official leaderboard
9 Kimi K3 1,482 ±291.9 high Jul 2026 Official leaderboard
10 GLM-5.3 1,482 ±291.9 high Aug 2026 Official leaderboard
11 Grok 4.7 1,482 ±291.9 high Sep 2026 Official leaderboard
12 GPT-6 Luna 1,380 ±136 high Sep 2026 Official leaderboard
13 GPT-5.6 Terra 1,276 ±257.6 high Jul 2026 Official leaderboard
14 GPT-5.6 Luna 1,268 ±223.8 high Jul 2026 Official leaderboard
15 Clef 1,115 ±233.5 none Official leaderboard
16 Jev 1.13 973 ±290.5 none Official leaderboard
#ModelScore ±SettingDateSource
1 GPT-6 Astra 1,901 ±180.2 high Sep 2026 Official leaderboard
2 GPT-6.1 Sol 1,847 ±235.2 high Sep 2026 Official leaderboard
3 Gemini 3.8 Flash 1,744 ±289.4 high Sep 2026 Official leaderboard
4 GPT-6 Sol 1,641 ±138.3 high Sep 2026 Official leaderboard
5 Claude Fable 5.1 1,614 ±284.3 high Sep 2026 Official leaderboard
6 Muse Spark 1.3 1,614 ±284.3 high Sep 2026 Official leaderboard
7 Claude Opus 5.5 1,614 ±284.3 high Sep 2026 Official leaderboard
8 GPT-5.6 Sol 1,566 ±243 high Jul 2026 Official leaderboard
9 Kimi K3 1,482 ±291.9 high Jul 2026 Official leaderboard
10 GLM-5.3 1,482 ±291.9 high Aug 2026 Official leaderboard
11 Grok 4.7 1,482 ±291.9 high Sep 2026 Official leaderboard
12 GPT-6 Luna 1,380 ±136 high Sep 2026 Official leaderboard
13 GPT-5.6 Terra 1,276 ±257.6 high Jul 2026 Official leaderboard
14 GPT-5.6 Luna 1,268 ±223.8 high Jul 2026 Official leaderboard

The best score, 1,901, costs $137 for the full run

Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol at high comes within 54.2 of the best for $11 for the full run, 13 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI Z.ai Google DeepMind Meta Cost frontier One model at each effort level
0 500 1,000 1,500 2,000 $1.00 $10 $100 $1,000 Cost of the full run, log scale GPT-6 Astra, high GPT-6.1 Sol, high Gemini 3.8 Flash, high Muse Spark 1.3, high GLM-5.3, high GPT-6 Luna, high GPT-5.6 Luna, high 0 500 1,000 1,500 2,000 $1.00 $10 $100 $1,000 Cost of the full run, log scale GPT-6 Astra, high Gemini 3.8 Flash, high

Source: Official Pokémon VGC Bench (Ricotoma) leaderboard

ModelEffortHarnessScoreCost of the full runOutput tokens
GPT-6 Astra high 1,901 $137
GPT-6.1 Sol high 1,847 $11
Gemini 3.8 Flash high 1,744 $8.33
GPT-6 Sol high 1,641 $28
Claude Fable 5.1 high 1,614 $78
Muse Spark 1.3 high 1,614 $6.34
Claude Opus 5.5 high 1,614 $15
GPT-5.6 Sol high 1,566 $22
Kimi K3 high 1,482 $12
GLM-5.3 high 1,482 $5.74
Grok 4.7 high 1,482 $18
GPT-6 Luna high 1,380 $1.64
GPT-5.6 Terra high 1,276 $8.70
GPT-5.6 Luna high 1,268 $1.40

The best score, 1,901, costs $137 for the full run

Runs on the cost frontier score higher than any run that's cheaper. GPT-6.1 Sol at high comes within 54.2 of the best for $11 for the full run, 13 times cheaper. The costs are the leaderboard's own estimates, so compare them only within this benchmark.

OpenAI Z.ai Google DeepMind Meta Cost frontier One model at each effort level
0 500 1,000 1,500 2,000 $1.00 $10 $100 $1,000 Cost of the full run, log scale GPT-6 Astra, high GPT-6.1 Sol, high Gemini 3.8 Flash, high Muse Spark 1.3, high GLM-5.3, high GPT-6 Luna, high GPT-5.6 Luna, high 0 500 1,000 1,500 2,000 $1.00 $10 $100 $1,000 Cost of the full run, log scale GPT-6 Astra, high Gemini 3.8 Flash, high

Source: Official Pokémon VGC Bench (Ricotoma) leaderboard

ModelEffortHarnessScoreCost of the full runOutput tokens
GPT-6 Astra high 1,901 $137
GPT-6.1 Sol high 1,847 $11
Gemini 3.8 Flash high 1,744 $8.33
GPT-6 Sol high 1,641 $28
Claude Fable 5.1 high 1,614 $78
Muse Spark 1.3 high 1,614 $6.34
Claude Opus 5.5 high 1,614 $15
GPT-5.6 Sol high 1,566 $22
Kimi K3 high 1,482 $12
GLM-5.3 high 1,482 $5.74
Grok 4.7 high 1,482 $18
GPT-6 Luna high 1,380 $1.64
GPT-5.6 Terra high 1,276 $8.70
GPT-5.6 Luna high 1,268 $1.40

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.

OpenAI Anthropic Google DeepMind
Own leaderboard Not tested since Sep 2026
GPT-6 Astra 1,901

Source: Official Pokémon VGC Bench (Ricotoma) 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
1,200 1,400 1,600 1,800 2,000 1,200 1,400 1,600 1,800 2,000

Source: Official Pokémon VGC Bench (Ricotoma) 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 (16 entries).
  • Pass Models scored 14 models we track, plus 2 other entries on its leaderboard.
  • Pass Newest score The newest is from September 2026, for GPT-6.1 Sol.
  • Pass Frontier models 4 of the top 10 have a score, led by GPT-6 Astra (#4).
  • Note Headroom Scored as a rating, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on ricotoma.com: 14 rows for models we track and 2 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.

How we check