Benchmark Almanac

The Aggregate Lichess Pairwise Strength

Gemini 3.8 Flash 88% leads since September 2026
Not in model cards

Models read two anonymized chess games and choose which designated player had the higher pregame Lichess rapid rating. Accuracy counts 25 choices.

The maker ranks 19 models. Three tied at 22 correct choices. The games also appear in the numerical rating test.

Kind
Puzzles and chess
Level
School
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
GPT-6.2 Astra #1 on the capability index
Last model added
November 2026
Scores refreshed
November 20th, 2026
19
Models scored on its own leaderboard

3 models share the top score of 88%

Best score per model from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best.

Source: Official The Aggregate Lichess Pairwise Strength leaderboard

#ModelScoreSettingDateSource
1 Gemini 3.8 Flash 88% Medium reasoning Sep 2026 Official leaderboard
2 Claude Opus 5.5 88% Medium reasoning Sep 2026 Official leaderboard
3 Claude Sonnet 5.5 88% Medium reasoning Sep 2026 Official leaderboard
4 Gemini 3.1 Pro 84% Medium reasoning Feb 2026 Official leaderboard
5 Gemini 3.5 Flash 84% Medium reasoning May 2026 Official leaderboard
6 Qwen 3.8 Max 84% prime, Medium reasoning Aug 2026 Official leaderboard
7 Gemini 3.7 Flash 84% Medium reasoning Aug 2026 Official leaderboard
8 Gemini 3 Flash 80% Medium reasoning Dec 2025 Official leaderboard
9 GPT-5.6 Sol 80% Medium reasoning Jul 2026 Official leaderboard
10 Gemini 3.6 Flash 80% Medium reasoning Jul 2026 Official leaderboard
11 Claude Fable 5.1 80% Medium reasoning Sep 2026 Official leaderboard
12 GPT-6.2 Sol 80% Medium reasoning Nov 2026 Official leaderboard
13 GPT-6 Sol 76% Medium reasoning Sep 2026 Official leaderboard
14 GPT-6.1 Sol 76% Medium reasoning Sep 2026 Official leaderboard
15 GPT-6.2 Astra 76% Medium reasoning Nov 2026 Official leaderboard
16 GPT-5.6 Luna 72% Medium reasoning Jul 2026 Official leaderboard
17 GLM-5.3-Flash 72% Medium reasoning Aug 2026 Official leaderboard
18 GPT-6 Astra 72% Medium reasoning Sep 2026 Official leaderboard
19 Claude Fable 5.2 72% Medium reasoning Nov 2026 Official leaderboard

3 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.

Google DeepMind
Own leaderboard Passed 85% in Sep 2026, by Gemini 3.8 Flash

Source: Official The Aggregate Lichess Pairwise Strength leaderboard

Gemini 3.8 Flash on the official leaderboard passed 85% in September 2026

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 Best so far
0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Gemini 3.8 Flash Gemini 3.1 Pro 0% 20% 40% 60% 80% 100% 2026 2027 Near the ceiling (85%) Gemini 3.8 Flash Gemini 3 Flash

Source: Official The Aggregate Lichess Pairwise Strength 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 (19 entries).
  • Pass Models scored 19 models we track.
  • Pass Newest score The newest is from November 2026, for GPT-6.2 Astra.
  • Pass Frontier models 7 of the top 10 have a score, led by GPT-6.2 Astra (#1).
  • Note Headroom Saturated. The best is 88%, past 85% since September 2026.
Leaderboard import 3 pass
  • Pass Importer We read the board on theaggregate.ai: 19 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