Benchmark Almanac

TavernBench

GPT-6 Astra 95.6 leads since October 2026
Not in model cards

Agents build a Hearthstone Battlegrounds player through research, simulator updates, and live games.

The October 2026 paper reports a comparison with top players. The abstract does not state the model count or best score.

Released
October 2026
Kind
Video games
Level
Expert
Scored
Settled by events
Answers
Agent task
Tasks
All public
Measures
Capability
Language
English
In and out
Text, Code → Code, Actions
Interaction
Multi-agent
Refresh
Live
Run by
Anyone
Strongest model tested
GPT-6 Astra #4 on the capability index
Last model added
September 2026
Scores refreshed
November 20th, 2026
5
Entries in its paper, 4 models we track

GPT-6 Astra leads with 95.6 among models released by September 2026 GPT-6 Astra leads with 95.6 among models released by September 2026

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this is the plain mean of the eight tool-use category scores. 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. 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:

  1. 1 GPT-6 Astra 95.6
  2. 2 GLM-5.3 79.0
  3. 3 DeepSeek V4.1 Flash 61.8
  4. 4 Kimi K2.6 57.8
  5. 5 Intern-S2-Preview 40.4

Source: The TavernBench paper

#EntryScoreSettingDateSource
1 GPT-6 Astra 95.6 Sep 2026 Official leaderboard
2 GLM-5.3 79.0 Aug 2026 Official leaderboard
3 DeepSeek V4.1 Flash 61.8 Sep 2026 Official leaderboard
4 Kimi K2.6 57.8 Apr 2026 Official leaderboard
5 Intern-S2-Preview 40.4 Official leaderboard
#ModelScoreSettingDateSource
1 GPT-6 Astra 95.6 Sep 2026 Official leaderboard
2 GLM-5.3 79.0 Aug 2026 Official leaderboard
3 DeepSeek V4.1 Flash 61.8 Sep 2026 Official leaderboard
4 Kimi K2.6 57.8 Apr 2026 Official leaderboard

Number one over time

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

OpenAI
Benchmark paper Not tested since Oct 2026

Source: The TavernBench 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
50.0 60.0 70.0 80.0 90.0 100.0 2026 50.0 60.0 70.0 80.0 90.0 100.0 2026

Source: Official TavernBench 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 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 benchmark’s paper (5 entries).
  • Pass Models scored 4 models we track, plus 1 other entry on its leaderboard.
  • Pass Newest score The newest is from September 2026, for DeepSeek V4.1 Flash.
  • Note Frontier models Only 1 of the top 10 has a score. The strongest tested is GPT-6 Astra (#4).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 4 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.

How we check