The Aggregate Lichess Pairwise Strength
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
- 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
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.
- 88.0
Gemini 3.8 Flash
- 88.0 Claude Opus 5.5
- 88.0 Claude Sonnet 5.5
- 84.0
Gemini 3.1 Pro
- 84.0
Gemini 3.5 Flash
- 84.0
Qwen 3.8 Max
- 84.0
Gemini 3.7 Flash
- 80.0
Gemini 3 Flash
- 80.0 GPT-5.6 Sol
- 80.0
Gemini 3.6 Flash
- 80.0 Claude Fable 5.1
- 80.0 GPT-6.2 Sol
- 76.0 GPT-6 Sol
- 76.0 GPT-6.1 Sol
- 76.0 GPT-6.2 Astra
- 72.0 GPT-5.6 Luna
- 72.0 GLM-5.3-Flash
- 72.0 GPT-6 Astra
- 72.0 Claude Fable 5.2
- 1
Gemini 3.8 Flash Medium reasoning 88%
- 2 Claude Opus 5.5 Medium reasoning 88%
- 3 Claude Sonnet 5.5 Medium reasoning 88%
- 4
Gemini 3.1 Pro Medium reasoning 84%
- 5
Gemini 3.5 Flash Medium reasoning 84%
- 6
Qwen 3.8 Max prime, Medium reasoning 84%
- 7
Gemini 3.7 Flash Medium reasoning 84%
- 8
Gemini 3 Flash Medium reasoning 80%
- 9 GPT-5.6 Sol Medium reasoning 80%
- 10
Gemini 3.6 Flash Medium reasoning 80%
- 11 Claude Fable 5.1 Medium reasoning 80%
- 12 GPT-6.2 Sol Medium reasoning 80%
- 13 GPT-6 Sol Medium reasoning 76%
- 14 GPT-6.1 Sol Medium reasoning 76%
- 15 GPT-6.2 Astra Medium reasoning 76%
- 16 GPT-5.6 Luna Medium reasoning 72%
- 17 GLM-5.3-Flash Medium reasoning 72%
- 18 GPT-6 Astra Medium reasoning 72%
- 19 Claude Fable 5.2 Medium reasoning 72%
Source: Official The Aggregate Lichess Pairwise Strength leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 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 | | 84% | Medium reasoning | Feb 2026 | Official leaderboard |
| 5 | | 84% | Medium reasoning | May 2026 | Official leaderboard |
| 6 | | 84% | prime, Medium reasoning | Aug 2026 | Official leaderboard |
| 7 | | 84% | Medium reasoning | Aug 2026 | Official leaderboard |
| 8 | | 80% | Medium reasoning | Dec 2025 | Official leaderboard |
| 9 | GPT-5.6 Sol | 80% | Medium reasoning | Jul 2026 | Official leaderboard |
| 10 | | 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.
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.
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
- 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.