PokéBench: Raw Vision + Buttons
Models play Pokémon Red from screenshots using eight Game Boy buttons. Game memory verifies ten milestones, with fewer turns breaking ties.
The maker ranks 19 models using prompt rvb4. Each model gets up to 1,000 turns to earn the Boulder Badge.
- Made by
- Cody Harris
- Released
- October 2026
- Kind
- Video games
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- Pokémon Red and Blue
- Items from
- Written by experts
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- A version of another benchmark
- Strongest model tested
- Claude Fable 5.2 #2 on the capability index
- Last model added
- November 2026
- Scores refreshed
- November 20th, 2026
8 models share the top score of 10.0 8 models share the top score of 10.0
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.
- 10.0 Claude Fable 5.1
- 10.0 GPT-6 Astra
- 10.0 Claude Opus 5.5
- 10.0 Claude Sonnet 5.5
- 10.0 GPT-6.1 Sol
- 10.0
Gemini 4 Argon
- 10.0 GPT-6.1 Terra
- 10.0 Claude Fable 5.2
- 7.00 Kimi K3.1 Pro
- 5.00
DeepSeek V4.1 Flash 1017
- 5.00
Tencent Hy4
- 4.00 Claude Haiku 5.5
- 1.00
Qwen 3.8 27B
- 1.00 GLM-5.3-Flash
- 1.00 GPT-6 Luna
- 0.00
Gemma 4 26B A4B
- 0.00
Gemma 4 31B IT
- 0.00
Muse Glimmer
- 0.00 Qwen3-VL 30B
- 1 Claude Fable 5.1 rvb4, harness v2, high 10.0
- 2 GPT-6 Astra rvb4, harness v2, high 10.0
- 3 Claude Opus 5.5 rvb4, harness v2, high 10.0
- 4 Claude Sonnet 5.5 rvb4, harness v2, high 10.0
- 5 GPT-6.1 Sol rvb4, harness v2, high 10.0
- 6
Gemini 4 Argon rvb4, harness v2, high 10.0
- 7 GPT-6.1 Terra rvb4, harness v2, high 10.0
- 8 Claude Fable 5.2 rvb4, harness v2, high 10.0
- 9 Kimi K3.1 Pro rvb4, harness v2, high 7.00
- 10
DeepSeek V4.1 Flash 1017 rvb4, harness v2, high 5.00
- 11
Tencent Hy4 rvb4, harness v2, high 5.00
- 12 Claude Haiku 5.5 rvb4, harness v2, high 4.00
- 13
Qwen 3.8 27B rvb4, harness v2, high 1.00
- 14 GLM-5.3-Flash rvb4, harness v2, high 1.00
- 15 GPT-6 Luna rvb4, harness v2, high 1.00
- 16
Gemma 4 26B A4B rvb4, harness v2, high 0.00
- 17
Gemma 4 31B IT rvb4, harness v2, high 0.00
- 18
Muse Glimmer rvb4, harness v2, high 0.00
- 19 Qwen3-VL 30B rvb4, harness v2, high 0.00
Source: Official PokéBench: Raw Vision + Buttons leaderboard
- 10.0 Claude Fable 5.1
- 10.0 GPT-6 Astra
- 10.0 Claude Opus 5.5
- 10.0 Claude Sonnet 5.5
- 10.0 GPT-6.1 Sol
- 10.0
Gemini 4 Argon
- 10.0 GPT-6.1 Terra
- 10.0 Claude Fable 5.2
- 7.00 Kimi K3.1 Pro
- 5.00
DeepSeek V4.1 Flash 1017
- 5.00
Tencent Hy4
- 4.00 Claude Haiku 5.5
- 1.00
Qwen 3.8 27B
- 1.00 GLM-5.3-Flash
- 1.00 GPT-6 Luna
- 0.00
Gemma 4 26B A4B
- 0.00
Gemma 4 31B IT
- 0.00
Muse Glimmer
- 1 Claude Fable 5.1 rvb4, harness v2, high 10.0
- 2 GPT-6 Astra rvb4, harness v2, high 10.0
- 3 Claude Opus 5.5 rvb4, harness v2, high 10.0
- 4 Claude Sonnet 5.5 rvb4, harness v2, high 10.0
- 5 GPT-6.1 Sol rvb4, harness v2, high 10.0
- 6
Gemini 4 Argon rvb4, harness v2, high 10.0
- 7 GPT-6.1 Terra rvb4, harness v2, high 10.0
- 8 Claude Fable 5.2 rvb4, harness v2, high 10.0
- 9 Kimi K3.1 Pro rvb4, harness v2, high 7.00
- 10
DeepSeek V4.1 Flash 1017 rvb4, harness v2, high 5.00
- 11
Tencent Hy4 rvb4, harness v2, high 5.00
- 12 Claude Haiku 5.5 rvb4, harness v2, high 4.00
- 13
Qwen 3.8 27B rvb4, harness v2, high 1.00
- 14 GLM-5.3-Flash rvb4, harness v2, high 1.00
- 15 GPT-6 Luna rvb4, harness v2, high 1.00
- 16
Gemma 4 26B A4B rvb4, harness v2, high 0.00
- 17
Gemma 4 31B IT rvb4, harness v2, high 0.00
- 18
Muse Glimmer rvb4, harness v2, high 0.00
Source: Official PokéBench: Raw Vision + Buttons leaderboard
| # | Entry | Score | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 2 | GPT-6 Astra | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 3 | Claude Opus 5.5 | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 4 | Claude Sonnet 5.5 | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 5 | GPT-6.1 Sol | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 6 | | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 7 | GPT-6.1 Terra | 10.0 | rvb4, harness v2, high | Oct 2026 | Oct 2026 | Official leaderboard | |
| 8 | Claude Fable 5.2 | 10.0 | rvb4, harness v2, high | Nov 2026 | Nov 2026 | youtube.com | Official leaderboard |
| 9 | Kimi K3.1 Pro | 7.00 | rvb4, harness v2, high | Oct 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 10 | | 5.00 | rvb4, harness v2, high | Oct 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 11 | | 5.00 | rvb4, harness v2, high | Nov 2026 | Nov 2026 | Official leaderboard | |
| 12 | Claude Haiku 5.5 | 4.00 | rvb4, harness v2, high | Oct 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 13 | | 1.00 | rvb4, harness v2, high | Aug 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 14 | GLM-5.3-Flash | 1.00 | rvb4, harness v2, high | Aug 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 15 | GPT-6 Luna | 1.00 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 16 | | 0.00 | rvb4, harness v2, high | Apr 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 17 | | 0.00 | rvb4, harness v2, high | Apr 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 18 | | 0.00 | rvb4, harness v2, high | Aug 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 19 | Qwen3-VL 30B | 0.00 | rvb4, harness v2, high | Oct 2026 | youtube.com | Official leaderboard |
| # | Model | Score | Setting | Released | Run on | Link | Source |
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5.1 | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 2 | GPT-6 Astra | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 3 | Claude Opus 5.5 | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 4 | Claude Sonnet 5.5 | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 5 | GPT-6.1 Sol | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 6 | | 10.0 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 7 | GPT-6.1 Terra | 10.0 | rvb4, harness v2, high | Oct 2026 | Oct 2026 | Official leaderboard | |
| 8 | Claude Fable 5.2 | 10.0 | rvb4, harness v2, high | Nov 2026 | Nov 2026 | youtube.com | Official leaderboard |
| 9 | Kimi K3.1 Pro | 7.00 | rvb4, harness v2, high | Oct 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 10 | | 5.00 | rvb4, harness v2, high | Oct 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 11 | | 5.00 | rvb4, harness v2, high | Nov 2026 | Nov 2026 | Official leaderboard | |
| 12 | Claude Haiku 5.5 | 4.00 | rvb4, harness v2, high | Oct 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 13 | | 1.00 | rvb4, harness v2, high | Aug 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 14 | GLM-5.3-Flash | 1.00 | rvb4, harness v2, high | Aug 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 15 | GPT-6 Luna | 1.00 | rvb4, harness v2, high | Sep 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 16 | | 0.00 | rvb4, harness v2, high | Apr 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 17 | | 0.00 | rvb4, harness v2, high | Apr 2026 | Oct 2026 | youtube.com | Official leaderboard |
| 18 | | 0.00 | rvb4, harness v2, high | Aug 2026 | Oct 2026 | youtube.com | Official leaderboard |
Rankings by part
We read 10 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Left the house, Got a starter and Reached Route 1. Gemini 4 Argon leads 6 of them, and Claude Fable 5.2 leads the other 4. Arrows show how far a model moved from its overall rank among the models we track.
Left the house
15 models we track have a score here.
- 1 Claude Fable 5.2 ↑7 12.0
- 2 GPT-6.1 Terra ↑5 13.0
- 3 GPT-6.1 Sol ↑2 14.0
- 4 Claude Opus 5.5 ↓1 15.0
- 5
Gemini 4 Argon ↑1 15.0
- 6 Claude Sonnet 5.5 ↓2 17.0
- 7 GPT-6 Astra ↓5 19.0
- 8
Tencent Hy4 ↑3 19.0
- 9 Claude Fable 5.1 ↓8 22.0
- 10 Kimi K3.1 Pro ↓1 25.0
Got a starter
12 models we track have a score here.
- 1 Claude Fable 5.2 ↑7 23.0
- 2
Gemini 4 Argon ↑4 24.0
- 3 Claude Opus 5.5 29.0
- 4 GPT-6 Astra ↓2 30.0
- 5 GPT-6.1 Sol 32.0
- 6 Claude Fable 5.1 ↓5 33.0
- 7 GPT-6.1 Terra 34.0
- 8 Claude Sonnet 5.5 ↓4 35.0
- 9
Tencent Hy4 ↑2 42.0
- 10 Kimi K3.1 Pro ↓1 43.0
Reached Route 1
12 models we track have a score here.
- 1
Gemini 4 Argon ↑5 41.0
- 2 Claude Fable 5.2 ↑6 44.0
- 3 GPT-6 Astra ↓1 57.0
- 4 Claude Opus 5.5 ↓1 57.0
- 5 GPT-6.1 Sol 58.0
- 6 Claude Sonnet 5.5 ↓2 59.0
- 7 Claude Fable 5.1 ↓6 61.0
- 8 GPT-6.1 Terra ↓1 61.0
- 9 Claude Haiku 5.5 ↑3 93.0
- 10
Tencent Hy4 ↑1 104.0
Reached Viridian City
12 models we track have a score here.
- 1
Gemini 4 Argon ↑5 54.0
- 2 Claude Fable 5.2 ↑6 66.0
- 3 Claude Opus 5.5 73.0
- 4 GPT-6 Astra ↓2 80.0
- 5 Claude Sonnet 5.5 ↓1 81.0
- 6 Claude Fable 5.1 ↓5 84.0
- 7 GPT-6.1 Terra 110.0
- 8 GPT-6.1 Sol ↓3 122.0
- 9 Kimi K3.1 Pro 164.0
- 10 Claude Haiku 5.5 ↑2 166.0
Got Oak's Parcel
11 models we track have a score here.
- 1
Gemini 4 Argon ↑5 60.0
- 2 Claude Opus 5.5 ↑1 79.0
- 3 Claude Fable 5.2 ↑5 79.0
- 4 Claude Fable 5.1 ↓3 98.0
- 5 GPT-6 Astra ↓3 100.0
- 6 Claude Sonnet 5.5 ↓2 136.0
- 7 GPT-6.1 Sol ↓2 141.0
- 8 GPT-6.1 Terra ↓1 205.0
- 9
Tencent Hy4 ↑2 346.0
- 10 Kimi K3.1 Pro ↓1 408.0
Got the Pokédex
9 models we track have a score here.
- 1
Gemini 4 Argon ↑5 88.0
- 2 Claude Fable 5.2 ↑6 103.0
- 3 Claude Opus 5.5 115.0
- 4 GPT-6 Astra ↓2 135.0
- 5 Claude Fable 5.1 ↓4 139.0
- 6 GPT-6.1 Sol ↓1 176.0
- 7 Claude Sonnet 5.5 ↓3 194.0
- 8 GPT-6.1 Terra ↓1 241.0
- 9 Kimi K3.1 Pro 688.0
Entered Viridian Forest
9 models we track have a score here.
- 1
Gemini 4 Argon ↑5 124.0
- 2 Claude Fable 5.2 ↑6 167.0
- 3 Claude Opus 5.5 179.0
- 4 GPT-6 Astra ↓2 196.0
- 5 GPT-6.1 Sol 240.0
- 6 Claude Fable 5.1 ↓5 242.0
- 7 Claude Sonnet 5.5 ↓3 291.0
- 8 GPT-6.1 Terra ↓1 343.0
- 9 Kimi K3.1 Pro 769.0
Reached Pewter City
8 models we track have a score here.
- 1 Claude Fable 5.2 ↑7 254.0
- 2
Gemini 4 Argon ↑4 255.0
- 3 GPT-6 Astra ↓1 348.0
- 4 Claude Opus 5.5 ↓1 383.0
- 5 GPT-6.1 Sol 398.0
- 6 Claude Fable 5.1 ↓5 428.0
- 7 Claude Sonnet 5.5 ↓3 435.0
- 8 GPT-6.1 Terra ↓1 618.0
Entered Brock's Gym
8 models we track have a score here.
- 1
Gemini 4 Argon ↑5 263.0
- 2 Claude Fable 5.2 ↑6 274.0
- 3 GPT-6 Astra ↓1 378.0
- 4 Claude Opus 5.5 ↓1 409.0
- 5 GPT-6.1 Sol 442.0
- 6 Claude Fable 5.1 ↓5 452.0
- 7 Claude Sonnet 5.5 ↓3 452.0
- 8 GPT-6.1 Terra ↓1 655.0
Beat Brock (Boulder Badge)
8 models we track have a score here.
- 1 Claude Fable 5.2 ↑7 294.0
- 2
Gemini 4 Argon ↑4 320.0
- 3 Claude Opus 5.5 444.0
- 4 GPT-6 Astra ↓2 478.0
- 5 Claude Fable 5.1 ↓4 529.0
- 6 GPT-6.1 Terra ↑1 746.0
- 7 GPT-6.1 Sol ↓2 758.0
- 8 Claude Sonnet 5.5 ↓4 925.0
The best score, 10.0, costs $7.62 for the full run
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 PokéBench: Raw Vision + Buttons leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.1 | rvb4, harness v2, high | 10.0 | $50 | 762,779 | |
| GPT-6 Astra | rvb4, harness v2, high | 10.0 | $58 | 54,495 | |
| Claude Opus 5.5 | rvb4, harness v2, high | 10.0 | $7.62 | 224,834 | |
| Claude Sonnet 5.5 | rvb4, harness v2, high | 10.0 | $14 | 515,015 | |
| GPT-6.1 Sol | rvb4, harness v2, high | 10.0 | $33 | 154,134 | |
| rvb4, harness v2, high | 10.0 | $11 | 264,789 | ||
| GPT-6.1 Terra | rvb4, harness v2, high | 10.0 | $14 | 113,814 | |
| Claude Fable 5.2 | rvb4, harness v2, high | 10.0 | $11 | 208,525 | |
| Kimi K3.1 Pro | rvb4, harness v2, high | 7.00 | $15 | 800,087 | |
| rvb4, harness v2, high | 5.00 | $1.87 | 2,787,675 | ||
| rvb4, harness v2, high | 5.00 | $33 | 22,199,749 | ||
| Claude Haiku 5.5 | rvb4, harness v2, high | 4.00 | $1.42 | 1,096,238 | |
| rvb4, harness v2, high | 1.00 | 209,979 | |||
| GLM-5.3-Flash | rvb4, harness v2, high | 1.00 | $4.57 | 1,093,386 | |
| GPT-6 Luna | rvb4, harness v2, high | 1.00 | $3.59 | 491,193 | |
| rvb4, harness v2, high | 0.00 | 224,504 | |||
| rvb4, harness v2, high | 0.00 | 75,162 | |||
| rvb4, harness v2, high | 0.00 | 857,362 |
The best score, 10.0, costs $7.62 for the full run
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 PokéBench: Raw Vision + Buttons leaderboard
| Model | Effort | Harness | Score | Cost of the full run | Output tokens |
|---|---|---|---|---|---|
| Claude Fable 5.1 | rvb4, harness v2, high | 10.0 | $50 | 762,779 | |
| GPT-6 Astra | rvb4, harness v2, high | 10.0 | $58 | 54,495 | |
| Claude Opus 5.5 | rvb4, harness v2, high | 10.0 | $7.62 | 224,834 | |
| Claude Sonnet 5.5 | rvb4, harness v2, high | 10.0 | $14 | 515,015 | |
| GPT-6.1 Sol | rvb4, harness v2, high | 10.0 | $33 | 154,134 | |
| rvb4, harness v2, high | 10.0 | $11 | 264,789 | ||
| GPT-6.1 Terra | rvb4, harness v2, high | 10.0 | $14 | 113,814 | |
| Claude Fable 5.2 | rvb4, harness v2, high | 10.0 | $11 | 208,525 | |
| Kimi K3.1 Pro | rvb4, harness v2, high | 7.00 | $15 | 800,087 | |
| rvb4, harness v2, high | 5.00 | $1.87 | 2,787,675 | ||
| rvb4, harness v2, high | 5.00 | $33 | 22,199,749 | ||
| Claude Haiku 5.5 | rvb4, harness v2, high | 4.00 | $1.42 | 1,096,238 | |
| rvb4, harness v2, high | 1.00 | 209,979 | |||
| GLM-5.3-Flash | rvb4, harness v2, high | 1.00 | $4.57 | 1,093,386 | |
| GPT-6 Luna | rvb4, harness v2, high | 1.00 | $3.59 | 491,193 | |
| rvb4, harness v2, high | 0.00 | 224,504 | |||
| rvb4, harness v2, high | 0.00 | 75,162 | |||
| rvb4, harness v2, high | 0.00 | 857,362 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official PokéBench: Raw Vision + Buttons 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 PokéBench: Raw Vision + Buttons 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 (19 entries).
- Pass Models scored 18 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from November 2026, for Claude Fable 5.2.
- Pass Frontier models 8 of the top 10 have a score, led by Claude Fable 5.2 (#2).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on pokebench.tv: 18 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.