Benchmark Almanac

Poker Arena

Claude Opus 4.6 15730.0 leads since June 2026
Not in model cards

Models play no-limit Texas Hold’em across repeated sessions. The benchmark scores tournament chips and nine strategic dimensions, including memory and bluffing.

Claude Opus 4.6 won 15,730 chips with 14 first-place finishes among seven models in the June 2026 paper.

Released
June 2026
Kind
Multi-agent games
Level
Everyday
Scored
Settled by events
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Actions
Interaction
Multi-agent
Environment
Texas hold 'em
Items from
Live play or votes
Refresh
Live
Run by
Anyone
In views
Games, Agents, Kept fresh
Strongest model tested
GPT-5.4 #28 on the capability index
Last model added
March 2026
Scores refreshed
November 20th, 2026
7
Models scored in its paper

Claude Opus 4.6 leads with 15730.0 among models released by March 2026

Best score per model from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best.

The newest model with a score here came out in March 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Opus 4.6 15730.0
  2. 2 Grok 4 3705.0
  3. 3 DeepSeek-V3.1 -937.00
  4. 4 GPT-5.4 -1060.00
  5. 5 Gemini 3.1 Pro -2095.00
  6. 6 Qwen3-Max -2785.00
  7. 7 Kimi K2 Thinking -12558.00

Source: The Poker Arena paper

#ModelScoreSettingDateSource
1 Claude Opus 4.6 15730.0 Feb 2026 Official leaderboard
2 Grok 4 3705.0 Jul 2025 Official leaderboard
3 DeepSeek-V3.1 -937.00 Aug 2025 Official leaderboard
4 GPT-5.4 -1060.00 Mar 2026 Official leaderboard
5 Gemini 3.1 Pro -2095.00 Feb 2026 Official leaderboard
6 Qwen3-Max -2785.00 Sep 2025 Official leaderboard
7 Kimi K2 Thinking -12558.00 Nov 2025 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Anthropic
Benchmark paper Not tested since Jun 2026
Claude Opus 4.6 15730.0

Source: The Poker Arena paper

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
In the benchmark’s paper
-20000.00 -10000.00 0.00 10000.0 20000.0 2026 -20000.00 -10000.00 0.00 10000.0 20000.0 2026

Source: Official Poker Arena 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 8 months ago, in March 2026, for GPT-5.4. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (7 entries).
  • Pass Models scored 7 models we track.
  • Warning Newest score The newest came 8 months ago, in March 2026, for GPT-5.4.
  • Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5.4 (#28).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 7 rows for models we track 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