GTO Wizard Benchmark
Models play heads-up no-limit Texas Hold’em against GTO Wizard AI. AIVAT reduces variance while the benchmark reports poker winnings.
The March 2026 paper reports GPT-5.4 Extra High reasoning at -17.8 bb/100 and GPT-5.3 Extra High reasoning at -16 bb/100 against the solver.
- Made by
- GTO Wizard research team
- Released
- March 2026
- Kind
- Multi-agent games
- Level
- Expert
- Scored
- Settled by events
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Multi-agent
- Environment
- Texas hold 'em, APIs and tools
- Items from
- Live play or votes
- Refresh
- Live
- Run by
- Anyone
- In views
- Games, Agents, Kept fresh
- Strongest model tested
- GPT-5.6 Sol #14 on the capability index
- Last model added
- July 2026
- Scores refreshed
- November 20th, 2026
Pokermon tops the leaderboard with 2.29 GPT-5.5 leads with -9.23 among models released by July 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. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is GPT-5.5, at -9.23. This view shows only models we track, each at its best.
The newest model with a score here came out in July 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 15 more
- 2.29 Pokermon
- -0.41 Cerberus
- -1.99 odabasz
- -2.10 Immortal
- -2.46 Ablion
- -2.61 MikkaMakka
- -2.65 Competitor
- -3.08 Bitcrumbs
- -3.52 PokerBotV1
- -3.70 Alex
- -4.25 Marvel
- -4.46 Roman_SL
- -4.47 Trainer
- -4.89 No Mercy
- -4.95 betaholdem
- -5.11 No Mercy v2
- -5.40 GPT-6
- -5.56 mitochondria
- -5.60 LaughingTroll
- -6.09 VDPAI
- -6.44 VDPAI.AG2
- -6.51 Swan2
- -6.92 eva
- -6.98 LordHU
- -7.66 The Speckled Bluff
- -7.84 kevin
- -8.36 Edpoker
- -8.65 MagicMike
- -9.23 GPT-5.5
- -9.53 PatchSolver
- -9.87 broke
- -10.12 SHUTDOWN
- -10.24 Hao Pokerbot
- -10.61 Gravel
- -10.84 Bulochka
- -10.87 evaBot01
- -11.23 fifth-street-irregulars
- -12.17 Oryx
- -12.28 Swan
- -12.59 tangtang's agent
- -12.70 Halcyon
- -13.17 GPT 5.5 Xhigh reproduction
- -13.17 Pi
- -13.79 cat
- -14.40 AlphaPoker
- -14.85 RabbitHunt
- -15.02 pokerbot (working name)
- -15.05 PokerBot
- -15.43 GPT-5.6 Sol
- -15.51 UdelaR Bot
- -15.65 dean
- -15.65 Umbra
- -16.02 Oski
- -16.04 GPT-5.3
- -16.05 LLM+Poker
- -16.21 Midas
- -16.46 harvey
- -16.57 fmventuresV1
- -16.81 holdem-lab
- -17.00 Claude Opus 4.7 reproduction
- -17.20 Esther Aspasie
- -17.54 markluce
- -17.59 Dog
- -17.70 Boreal
- -17.84 GPT-5.4
- -18.06 Sean-Poker-4B
- -18.29 sidecard
- -18.42 aipmtw
- -18.54 Pokea
- -18.75 Riverline
- -19.23 Eddie Poker
- -19.44 testbot
- -19.46 Phoker 0.1
- -20.09 EHO
- -20.24 HUB
- -20.35 Claude Opus 4.6
- -20.89 PokerSkill
- -21.65 SempliceSL
- -22.26 Claude Opus 4.5
- -22.55 WinnerWinner
- -23.14 Haq-HU
- -23.24 pokerni
- -24.64 hu-adapt
- -25.54 PokerNi
- -25.75 Tributary
- -26.24 JulienAU
- -26.65 Perun
- -26.98 Poker AI
- -27.08 Nash Rambler
- -27.74 KingHU
- -27.97 skyproboost
- -30.27 PokerVision
- -30.83
Gemini 3.1 Pro
- -31.99 HitPoker
- -32.05 RobinAI
- -32.30 nn2
- -33.03 NoRegret
- -34.66 wizard-bot
- 1 Pokermon 2.29
- 2 Cerberus -0.41
- 3 odabasz -1.99
- 4 Immortal -2.10
- 5 Ablion -2.46
- 6 MikkaMakka -2.61
- 7 Competitor -2.65
- 8 Bitcrumbs -3.08
- 9 PokerBotV1 -3.52
- 10 Alex -3.70
- 11 Marvel -4.25
- 12 Roman_SL -4.46
- 13 Trainer -4.47
- 14 No Mercy -4.89
- 15 betaholdem -4.95
- 16 No Mercy v2 -5.11
- 17 GPT-6 Low Reasoning -5.40
- 18 mitochondria -5.56
- 19 LaughingTroll -5.60
- 20 VDPAI -6.09
- 21 VDPAI.AG2 -6.44
- 22 Swan2 -6.51
- 23 eva -6.92
- 24 LordHU -6.98
- 25 The Speckled Bluff -7.66
- 26 kevin -7.84
- 27 Edpoker -8.36
- 28 MagicMike -8.65
- 29 GPT-5.5 XHigh Reasoning -9.23
- 30 PatchSolver -9.53
- 31 broke -9.87
- 32 SHUTDOWN -10.12
- 33 Hao Pokerbot -10.24
- 34 Gravel -10.61
- 35 Bulochka -10.84
- 36 evaBot01 -10.87
- 37 fifth-street-irregulars -11.23
- 38 Oryx -12.17
- 39 Swan -12.28
- 40 tangtang's agent -12.59
- 41 Halcyon -12.70
- 42 GPT 5.5 Xhigh reproduction -13.17
- 43 Pi -13.17
- 44 cat -13.79
- 45 AlphaPoker -14.40
- 46 RabbitHunt -14.85
- 47 pokerbot (working name) -15.02
- 48 PokerBot -15.05
- 49 GPT-5.6 Sol XHigh Reasoning -15.43
- 50 UdelaR Bot -15.51
- 51 dean -15.65
- 52 Umbra -15.65
- 53 Oski -16.02
- 54 GPT-5.3 XHigh Reasoning -16.04
- 55 LLM+Poker -16.05
- 56 Midas -16.21
- 57 harvey -16.46
- 58 fmventuresV1 -16.57
- 59 holdem-lab -16.81
- 60 Claude Opus 4.7 reproduction -17.00
- 61 Esther Aspasie -17.20
- 62 markluce -17.54
- 63 Dog -17.59
- 64 Boreal -17.70
- 65 GPT-5.4 XHigh Reasoning -17.84
- 66 Sean-Poker-4B -18.06
- 67 sidecard -18.29
- 68 aipmtw -18.42
- 69 Pokea -18.54
- 70 Riverline -18.75
- 71 Eddie Poker -19.23
- 72 testbot -19.44
- 73 Phoker 0.1 -19.46
- 74 EHO -20.09
- 75 HUB -20.24
- 76 Claude Opus 4.6 -20.35
- 77 PokerSkill -20.89
- 78 SempliceSL -21.65
- 79 Claude Opus 4.5 -22.26
- 80 WinnerWinner -22.55
- 81 Haq-HU -23.14
- 82 pokerni -23.24
- 83 hu-adapt -24.64
- 84 PokerNi -25.54
- 85 Tributary -25.75
- 86 JulienAU -26.24
- 87 Perun -26.65
- 88 Poker AI -26.98
- 89 Nash Rambler -27.08
- 90 KingHU -27.74
- 91 skyproboost -27.97
- 92 PokerVision -30.27
- 93
Gemini 3.1 Pro -30.83
- 94 HitPoker -31.99
- 95 RobinAI -32.05
- 96 nn2 -32.30
- 97 NoRegret -33.03
- 98 wizard-bot -34.66
Source: Official GTO Wizard Benchmark leaderboard
- 1 GPT-5.5 XHigh Reasoning -9.23
- 2 GPT-5.6 Sol XHigh Reasoning -15.43
- 3 GPT-5.4 XHigh Reasoning -17.84
- 4 Claude Opus 4.6 -20.35
- 5 Claude Opus 4.5 -22.26
- 6
Gemini 3.1 Pro -30.83
Source: Official GTO Wizard Benchmark leaderboard
| # | Entry | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | Pokermon | 2.29 | Individual | Official leaderboard | ||
| 2 | Cerberus | -0.41 | Vrije Universiteit | Official leaderboard | ||
| 3 | odabasz | -1.99 | none | Official leaderboard | ||
| 4 | Immortal | -2.10 | IRT | Official leaderboard | ||
| 5 | Ablion | -2.46 | Ablion | Official leaderboard | ||
| 6 | MikkaMakka | -2.61 | Independent Research Team | Official leaderboard | ||
| 7 | Competitor | -2.65 | individual | Official leaderboard | ||
| 8 | Bitcrumbs | -3.08 | Individual | Official leaderboard | ||
| 9 | PokerBotV1 | -3.52 | Individual | Official leaderboard | ||
| 10 | Alex | -3.70 | Individual | Official leaderboard | ||
| 11 | Marvel | -4.25 | MIT | Official leaderboard | ||
| 12 | Roman_SL | -4.46 | Individual | Official leaderboard | ||
| 13 | Trainer | -4.47 | SL | Official leaderboard | ||
| 14 | No Mercy | -4.89 | Individual | Official leaderboard | ||
| 15 | betaholdem | -4.95 | individual | Official leaderboard | ||
| 16 | No Mercy v2 | -5.11 | individual | Official leaderboard | ||
| 17 | GPT-6 | -5.40 | Low Reasoning | OpenAI | Official leaderboard | |
| 18 | mitochondria | -5.56 | none | Official leaderboard | ||
| 19 | LaughingTroll | -5.60 | Individual | Official leaderboard | ||
| 20 | VDPAI | -6.09 | AcidPoker | Official leaderboard | ||
| 21 | VDPAI.AG2 | -6.44 | VDPAI | Official leaderboard | ||
| 22 | Swan2 | -6.51 | Vrije Universiteit | Official leaderboard | ||
| 23 | eva | -6.92 | individual | Official leaderboard | ||
| 24 | LordHU | -6.98 | Independent developer, university student (personal research project) | Official leaderboard | ||
| 25 | The Speckled Bluff | -7.66 | 221bb | Official leaderboard | ||
| 26 | kevin | -7.84 | ucsc | Official leaderboard | ||
| 27 | Edpoker | -8.36 | edpoker.online | Official leaderboard | ||
| 28 | MagicMike | -8.65 | University of Warsaw | Official leaderboard | ||
| 29 | GPT-5.5 | -9.23 | XHigh Reasoning | OpenAI | Apr 2026 | Official leaderboard |
| 30 | PatchSolver | -9.53 | Private | Official leaderboard | ||
| 31 | broke | -9.87 | personal | Official leaderboard | ||
| 32 | SHUTDOWN | -10.12 | Aaditya(SINGLE) | Official leaderboard | ||
| 33 | Hao Pokerbot | -10.24 | Ranella Studio | Official leaderboard | ||
| 34 | Gravel | -10.61 | MIT | Official leaderboard | ||
| 35 | Bulochka | -10.84 | GTOorGTFO | Official leaderboard | ||
| 36 | evaBot01 | -10.87 | individual | Official leaderboard | ||
| 37 | fifth-street-irregulars | -11.23 | 221bb | Official leaderboard | ||
| 38 | Oryx | -12.17 | Individual | Official leaderboard | ||
| 39 | Swan | -12.28 | Vrije Universiteit | Official leaderboard | ||
| 40 | tangtang's agent | -12.59 | Personal project | Official leaderboard | ||
| 41 | Halcyon | -12.70 | Individual | Official leaderboard | ||
| 42 | GPT 5.5 Xhigh reproduction | -13.17 | Random | Official leaderboard | ||
| 43 | Pi | -13.17 | Individual | Official leaderboard | ||
| 44 | cat | -13.79 | personal | Official leaderboard | ||
| 45 | AlphaPoker | -14.40 | Personal | Official leaderboard | ||
| 46 | RabbitHunt | -14.85 | Individual | Official leaderboard | ||
| 47 | pokerbot (working name) | -15.02 | independent | Official leaderboard | ||
| 48 | PokerBot | -15.05 | Independent (PokerBot project) | Official leaderboard | ||
| 49 | GPT-5.6 Sol | -15.43 | XHigh Reasoning | OpenAI | Jul 2026 | Official leaderboard |
| 50 | UdelaR Bot | -15.51 | UdelaR | Official leaderboard | ||
| 51 | dean | -15.65 | vdv | Official leaderboard | ||
| 52 | Umbra | -15.65 | Independent researcher (Proyecto Umbra) | Official leaderboard | ||
| 53 | Oski | -16.02 | UC Berkeley | Official leaderboard | ||
| 54 | GPT-5.3 | -16.04 | XHigh Reasoning | OpenAI | Official leaderboard | |
| 55 | LLM+Poker | -16.05 | Tsinghua University | Official leaderboard | ||
| 56 | Midas | -16.21 | Individual | Official leaderboard | ||
| 57 | harvey | -16.46 | individual | Official leaderboard | ||
| 58 | fmventuresV1 | -16.57 | fmventures | Official leaderboard | ||
| 59 | holdem-lab | -16.81 | none | Official leaderboard | ||
| 60 | Claude Opus 4.7 reproduction | -17.00 | Random | Official leaderboard | ||
| 61 | Esther Aspasie | -17.20 | Individual | Official leaderboard | ||
| 62 | markluce | -17.54 | Individual | Official leaderboard | ||
| 63 | Dog | -17.59 | Personal | Official leaderboard | ||
| 64 | Boreal | -17.70 | Duke | Official leaderboard | ||
| 65 | GPT-5.4 | -17.84 | XHigh Reasoning | OpenAI | Mar 2026 | Official leaderboard |
| 66 | Sean-Poker-4B | -18.06 | Independent researcher | Official leaderboard | ||
| 67 | sidecard | -18.29 | Independent researcher | Official leaderboard | ||
| 68 | aipmtw | -18.42 | Individual | Official leaderboard | ||
| 69 | Pokea | -18.54 | Wideworld E.I. | Official leaderboard | ||
| 70 | Riverline | -18.75 | Personal Project | Official leaderboard | ||
| 71 | Eddie Poker | -19.23 | Individual | Official leaderboard | ||
| 72 | testbot | -19.44 | self | Official leaderboard | ||
| 73 | Phoker 0.1 | -19.46 | Individual | Official leaderboard | ||
| 74 | EHO | -20.09 | EHO Design | Official leaderboard | ||
| 75 | HUB | -20.24 | WSV | Official leaderboard | ||
| 76 | Claude Opus 4.6 | -20.35 | Anthropic | Feb 2026 | Official leaderboard | |
| 77 | PokerSkill | -20.89 | Individual | Official leaderboard | ||
| 78 | SempliceSL | -21.65 | Individual developer | Official leaderboard | ||
| 79 | Claude Opus 4.5 | -22.26 | Anthropic | Nov 2025 | Official leaderboard | |
| 80 | WinnerWinner | -22.55 | Personal Project | Official leaderboard | ||
| 81 | Haq-HU | -23.14 | Individual | Official leaderboard | ||
| 82 | pokerni | -23.24 | Pokerni.com | Official leaderboard | ||
| 83 | hu-adapt | -24.64 | PokerBot research (private) | Official leaderboard | ||
| 84 | PokerNi | -25.54 | PokerNi | Official leaderboard | ||
| 85 | Tributary | -25.75 | Self | Official leaderboard | ||
| 86 | JulienAU | -26.24 | personal | Official leaderboard | ||
| 87 | Perun | -26.65 | individual | Official leaderboard | ||
| 88 | Poker AI | -26.98 | indenpent developer | Official leaderboard | ||
| 89 | Nash Rambler | -27.08 | Individual | Official leaderboard | ||
| 90 | KingHU | -27.74 | Individual | Official leaderboard | ||
| 91 | skyproboost | -27.97 | Independent developer | Official leaderboard | ||
| 92 | PokerVision | -30.27 | Independent developer (no organization) | Official leaderboard | ||
| 93 | | -30.83 | Feb 2026 | Official leaderboard | ||
| 94 | HitPoker | -31.99 | Private | Official leaderboard | ||
| 95 | RobinAI | -32.05 | Individual | Official leaderboard | ||
| 96 | nn2 | -32.30 | peilian-lab | Official leaderboard | ||
| 97 | NoRegret | -33.03 | Individual researcher | Official leaderboard | ||
| 98 | wizard-bot | -34.66 | Individual | Official leaderboard |
| # | Model | Score | Setting | Submitted by | Date | Source |
|---|---|---|---|---|---|---|
| 1 | GPT-5.5 | -9.23 | XHigh Reasoning | OpenAI | Apr 2026 | Official leaderboard |
| 2 | GPT-5.6 Sol | -15.43 | XHigh Reasoning | OpenAI | Jul 2026 | Official leaderboard |
| 3 | GPT-5.4 | -17.84 | XHigh Reasoning | OpenAI | Mar 2026 | Official leaderboard |
| 4 | Claude Opus 4.6 | -20.35 | Anthropic | Feb 2026 | Official leaderboard | |
| 5 | Claude Opus 4.5 | -22.26 | Anthropic | Nov 2025 | Official leaderboard | |
| 6 | | -30.83 | Feb 2026 | Official leaderboard |
3 models have held number one on the official leaderboard since its release in March 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official GTO Wizard Benchmark 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 GTO Wizard Benchmark 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 9 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 3 pass 2 notes
- Pass Independent runs Scores from the official leaderboard (98 entries).
- Pass Models scored 6 models we track, plus 92 other entries on its leaderboard.
- Pass Newest score The newest is from July 2026, for GPT-5.6 Sol.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.6 Sol (#14).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on benchmark.gtowizard.com: 6 rows for models we track and 92 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.